[{"suite":"so101","id":"block_stack/diffusion/eval_debug_task_cell_1_14h32m_25-jun-2026/ep000000","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000000","predictions":{"RoboJev-27B":0.0025183504295926825,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.005748540581680574,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.01734716816833724,"Liquid D1":0.006289901298656722,"Mercury Decide":0.0019267342245437627,"Cloudflare Clef":0.0755,"cloudflare/clef-flash":0.1447,"cloudflare/clef-omni":0.0295,"liquid/d1-ultra":0.03531702940233893,"open/intern-decision-4b":0.10592235395880453,"open/robojev-27b-v1@0.5":0.0006719318465893957,"open/robojev-27b":null,"open/robojev-4b-v2":0.0007554056122179476,"open/robojev-4b-v3@0.25":0.01098694372922182,"open/robojev-4b-v3@0.5":0.001481588165223606,"open/robojev-4b-v3@0.75":0.0006607800017573367,"open/robojev-4b-v3":0.0004448220671018799,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.022845356463294067,"respan/span-02":0.06447609,"typesafe/jev-1.13":0.03,"JEV-27B-VL (10 frames)":0.026035310133584955,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.003173828125}},{"suite":"so101","id":"block_stack/diffusion/eval_debug_task_cell_1_14h32m_25-jun-2026/ep000005","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000005","predictions":{"RoboJev-27B":0.0014206559824172583,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.007456629607564406,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.014102093061872014,"Liquid D1":0.14804720179063335,"Mercury Decide":0.0015978455876184507,"Cloudflare Clef":0.1121,"cloudflare/clef-flash":0.2566,"cloudflare/clef-omni":0.0595,"liquid/d1-ultra":0.056583661807353566,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.00026125844713487784,"open/robojev-27b":null,"open/robojev-4b-v2":0.0010793060165100975,"open/robojev-4b-v3@0.25":0.03308597952127457,"open/robojev-4b-v3@0.5":0.002856598198671041,"open/robojev-4b-v3@0.75":0.0008382685901687787,"open/robojev-4b-v3":0.00042130206657220226,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.08131811972502226,"respan/span-02":0.061709344,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.0008758310016869227,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.03369140625}},{"suite":"so101","id":"block_stack/diffusion/eval_debug_task_cell_1_14h32m_25-jun-2026/ep000008","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000008","predictions":{"RoboJev-27B":0.003881716331031443,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0031727820409172434,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.018687603188647182,"Liquid D1":0.01032815130080968,"Mercury Decide":0.0010322309503235263,"Cloudflare Clef":0.0458,"cloudflare/clef-flash":0.1168,"cloudflare/clef-omni":0.0308,"liquid/d1-ultra":0.037037988735086146,"open/intern-decision-4b":0.10012611628383591,"open/robojev-27b-v1@0.5":0.00037024944150217186,"open/robojev-27b":null,"open/robojev-4b-v2":0.0008635702282952242,"open/robojev-4b-v3@0.25":0.009708477184176445,"open/robojev-4b-v3@0.5":0.001481588165223606,"open/robojev-4b-v3@0.75":0.0005866612178080633,"open/robojev-4b-v3":0.00039902517764159984,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.022468340073568887,"respan/span-02":0.0516125,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.010504110430504497,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0032806396484375}},{"suite":"so101","id":"block_stack/diffusion/eval_debug_task_cell_1_14h32m_25-jun-2026/ep000010","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000010","predictions":{"RoboJev-27B":0.0016770201853901511,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.00823544860375082,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.016414306976552516,"Liquid D1":0.019124038428012403,"Mercury Decide":0.002472623581601231,"Cloudflare Clef":0.0823,"cloudflare/clef-flash":0.1671,"cloudflare/clef-omni":0.0398,"liquid/d1-ultra":0.038839452588039704,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.0001591107737120245,"open/robojev-27b":null,"open/robojev-4b-v2":0.000604373104847079,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.0015821797096241565,"open/robojev-4b-v3@0.75":0.0005527786854321331,"open/robojev-4b-v3":0.000377925780489165,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.041996276764238026,"respan/span-02":0.04458303,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.001218559304101774,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.005218505859375}},{"suite":"so101","id":"block_stack/diffusion/eval_debug_task_cell_1_14h32m_25-jun-2026/ep000012","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000012","predictions":{"RoboJev-27B":0.002639964941664959,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.0012232154977258162,"TypeSafe Jev 1.14":0.07,"Perplexity Decider":0.03395567924718968,"Liquid D1":0.017986213252027258,"Mercury Decide":0.003172682114967388,"Cloudflare Clef":0.0727,"cloudflare/clef-flash":0.2005,"cloudflare/clef-omni":0.0359,"liquid/d1-ultra":0.05658365866596999,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.00019008665595439986,"open/robojev-27b":null,"open/robojev-4b-v2":0.0010322309754180047,"open/robojev-4b-v3@0.25":0.01243165135383606,"open/robojev-4b-v3@0.5":0.002197092076271529,"open/robojev-4b-v3@0.75":0.0007442559788897843,"open/robojev-4b-v3":0.0004696544949846406,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.04127070472799077,"respan/span-02":0.050106928,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.002813622912086604,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01202392578125}},{"suite":"so101","id":"block_stack/diffusion/eval_debug_task_cell_1_14h32m_25-jun-2026/ep000014","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000014","predictions":{"RoboJev-27B":0.007661479695372484,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.015030047219223656,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.04005196004376779,"Liquid D1":0.39233681595684605,"Mercury Decide":0.0019267343911024666,"Cloudflare Clef":0.2085,"cloudflare/clef-flash":0.2817,"cloudflare/clef-omni":0.077,"liquid/d1-ultra":0.13865650101508367,"open/intern-decision-4b":0.4843206825122851,"open/robojev-27b-v1@0.5":0.006787354018702262,"open/robojev-27b":null,"open/robojev-4b-v2":0.005604465165684275,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.009275566578748366,"open/robojev-4b-v3@0.75":0.0030982660175204184,"open/robojev-4b-v3":0.0013178502752796797,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.13370778652742182,"respan/span-02":0.8990582,"typesafe/jev-1.13":0.31,"JEV-27B-VL (10 frames)":0.02517151973170798,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.033203125}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000000","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000000","predictions":{"RoboJev-27B":0.0011242048118210227,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.002995227330795917,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.01299871147392173,"Liquid D1":0.011687259028404494,"Mercury Decide":0.0009697518216138743,"Cloudflare Clef":0.1206,"cloudflare/clef-flash":0.1716,"cloudflare/clef-omni":0.0404,"liquid/d1-ultra":0.03883944522867475,"open/intern-decision-4b":0.13214384255458153,"open/robojev-27b-v1@0.5":0.000248344805916805,"open/robojev-27b":null,"open/robojev-4b-v2":0.0006607800349070568,"open/robojev-4b-v3@0.25":0.008577484637498856,"open/robojev-4b-v3@0.5":0.0015821797096241565,"open/robojev-4b-v3@0.75":0.0006607800017573367,"open/robojev-4b-v3":0.00035794164692484856,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.04037323335515253,"respan/span-02":0.020547701,"typesafe/jev-1.13":0.03,"JEV-27B-VL (10 frames)":0.026949704619493146,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00360107421875}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000002","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000002","predictions":{"RoboJev-27B":0.008964433989572588,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.041377677254886634,"TypeSafe Jev 1.14":0.07,"Perplexity Decider":0.038365807236957344,"Liquid D1":0.40733341443526055,"Mercury Decide":0.005911068330877026,"Cloudflare Clef":0.3296,"cloudflare/clef-flash":0.404,"cloudflare/clef-omni":0.06,"liquid/d1-ultra":0.13286532989413977,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.0015603359406987428,"open/robojev-27b":null,"open/robojev-4b-v2":0.0017624512139676404,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.010566189227213266,"open/robojev-4b-v3@0.75":0.0032876613688676065,"open/robojev-4b-v3":0.0013178502752796797,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.7009178011402112,"respan/span-02":0.12614083,"typesafe/jev-1.13":0.27,"JEV-27B-VL (10 frames)":0.023815468402659256,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.016357421875}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000004","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000004","predictions":{"RoboJev-27B":0.0011801793779970668,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.02939601393535684,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.022211271922597815,"Liquid D1":0.06754668550840877,"Mercury Decide":0.004609572739164718,"Cloudflare Clef":0.1378,"cloudflare/clef-flash":0.304,"cloudflare/clef-omni":0.0809,"liquid/d1-ultra":0.08174504332547765,"open/intern-decision-4b":0.1395062328236417,"open/robojev-27b-v1@0.5":0.0006612575073382185,"open/robojev-27b":null,"open/robojev-4b-v2":0.0010793060165100975,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.0019267347052741358,"open/robojev-4b-v3@0.75":0.0006607800017573367,"open/robojev-4b-v3":0.000377925780489165,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.07127355480669759,"respan/span-02":0.17300667,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.008364998193267302,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00628662109375}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000006","task":"Stack the colouful blocks on top of each other","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000006","predictions":{"RoboJev-27B":0.992156006046418,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.8701426511480571,"TypeSafe Jev 1.14":0.84,"Perplexity Decider":0.9446509655338444,"Liquid D1":0.993307149917757,"Mercury Decide":0.9940889299780985,"Cloudflare Clef":0.893,"cloudflare/clef-flash":0.8854,"cloudflare/clef-omni":0.0593,"liquid/d1-ultra":0.9484617360897487,"open/intern-decision-4b":0.6518947636686268,"open/robojev-27b-v1@0.5":0.9530767745201993,"open/robojev-27b":null,"open/robojev-4b-v2":0.9726532135583835,"open/robojev-4b-v3@0.25":0.9933071732521057,"open/robojev-4b-v3@0.5":0.9957666794968174,"open/robojev-4b-v3@0.75":0.9953077641775279,"open/robojev-4b-v3":0.9943083289415883,"openai/gpt-6-luna-decisions":0.98,"perplexity/pplx-decider-flash-v1.2":0.9757604931882731,"respan/span-02":0.9603064,"typesafe/jev-1.13":0.74,"JEV-27B-VL (10 frames)":0.9251885021052032,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.053466796875}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000007","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000007","predictions":{"RoboJev-27B":0.0016459942349581393,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.0465517891800519,"TypeSafe Jev 1.14":0.16,"Perplexity Decider":0.03390663030177512,"Liquid D1":0.5,"Mercury Decide":0.008577483782215753,"Cloudflare Clef":0.1922,"cloudflare/clef-flash":0.2225,"cloudflare/clef-omni":0.1031,"liquid/d1-ultra":0.106911738526731,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.0007729982802876919,"open/robojev-27b":null,"open/robojev-4b-v2":0.0010793060165100975,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.005872534859081002,"open/robojev-4b-v3@0.75":0.0011285254353805543,"open/robojev-4b-v3":0.0005527786044704864,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.15286343298218952,"respan/span-02":0.07395763,"typesafe/jev-1.13":0.15,"JEV-27B-VL (10 frames)":0.010370799065842621,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0240478515625}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000008","task":"Stack the colouful blocks on top of each other","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000008","predictions":{"RoboJev-27B":0.9954803832206028,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.9892387849599518,"TypeSafe Jev 1.14":0.91,"Perplexity Decider":0.9753636054995266,"Liquid D1":0.998073265286526,"Mercury Decide":0.9980732654423389,"Cloudflare Clef":0.9355,"cloudflare/clef-flash":0.861,"cloudflare/clef-omni":0.7526,"liquid/d1-ultra":0.9810937513537157,"open/intern-decision-4b":0.8678561574454184,"open/robojev-27b-v1@0.5":0.9975918595913987,"open/robojev-27b":null,"open/robojev-4b-v2":0.9456867326137218,"open/robojev-4b-v3@0.25":0.9940890073776245,"open/robojev-4b-v3@0.5":0.9962866673887035,"open/robojev-4b-v3@0.75":0.9960720983814959,"open/robojev-4b-v3":0.9965023978842734,"openai/gpt-6-luna-decisions":0.98,"perplexity/pplx-decider-flash-v1.2":0.9799633801762965,"respan/span-02":0.96729034,"typesafe/jev-1.13":0.76,"JEV-27B-VL (10 frames)":0.9298703647172754,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.90234375}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000009","task":"Stack the colouful blocks on top of each other","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000009","predictions":{"RoboJev-27B":0.994318151342157,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.9794935368122568,"TypeSafe Jev 1.14":0.9,"Perplexity Decider":0.9776202581221759,"Liquid D1":0.9896718482422546,"Mercury Decide":0.9984988176574098,"Cloudflare Clef":0.84,"cloudflare/clef-flash":0.8463,"cloudflare/clef-omni":0.5899,"liquid/d1-ultra":0.9871831273577484,"open/intern-decision-4b":0.8748864949022742,"open/robojev-27b-v1@0.5":0.9949599390342316,"open/robojev-27b":null,"open/robojev-4b-v2":0.02506949741812164,"open/robojev-4b-v3@0.25":0.9902915358543396,"open/robojev-4b-v3@0.5":0.9951742293531355,"open/robojev-4b-v3@0.75":0.9950214173047451,"open/robojev-4b-v3":0.9929359819003751,"openai/gpt-6-luna-decisions":0.98,"perplexity/pplx-decider-flash-v1.2":0.9815797262237644,"respan/span-02":0.97481805,"typesafe/jev-1.13":0.9,"JEV-27B-VL (10 frames)":0.862151998479698,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.74609375}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000010","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000010","predictions":{"RoboJev-27B":0.000775736238007539,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0002697949136189814,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.010769022394105654,"Liquid D1":0.09534947261117097,"Mercury Decide":0.0007096703145613268,"Cloudflare Clef":0.0927,"cloudflare/clef-flash":0.3627,"cloudflare/clef-omni":0.0416,"liquid/d1-ultra":0.04476157512522002,"open/intern-decision-4b":0.43758935794935333,"open/robojev-27b-v1@0.5":1.0313850226622834e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.0007898659476910931,"open/robojev-4b-v3@0.25":0.020332353189587593,"open/robojev-4b-v3@0.5":0.0019267347052741358,"open/robojev-4b-v3@0.75":0.0005208518753575066,"open/robojev-4b-v3":0.000377925780489165,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.18970030992043513,"respan/span-02":0.07336506,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.0018418265603280498,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0185546875}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000014","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000014","predictions":{"RoboJev-27B":0.001840710012670374,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.003335125729687539,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.017845687659273964,"Liquid D1":0.005554923757068447,"Mercury Decide":0.0010987309247130841,"Cloudflare Clef":0.0864,"cloudflare/clef-flash":0.125,"cloudflare/clef-omni":0.0376,"liquid/d1-ultra":0.04072481327203308,"open/intern-decision-4b":0.11840617139815589,"open/robojev-27b-v1@0.5":0.0006841466818771317,"open/robojev-27b":null,"open/robojev-4b-v2":0.0007554056122179476,"open/robojev-4b-v3@0.25":0.014063626527786255,"open/robojev-4b-v3@0.5":0.0019267347052741358,"open/robojev-4b-v3@0.75":0.0007012779614913075,"open/robojev-4b-v3":0.0004448220671018799,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.03283438169171399,"respan/span-02":0.04917768,"typesafe/jev-1.13":0.03,"JEV-27B-VL (10 frames)":0.01531293401861721,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006500244140625}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000015","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000015","predictions":{"RoboJev-27B":0.0010804020484183887,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0024202209303239826,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.012896309800455637,"Liquid D1":0.031143831883656593,"Mercury Decide":0.0011695102209948575,"Cloudflare Clef":0.0543,"cloudflare/clef-flash":0.1855,"cloudflare/clef-omni":0.0593,"liquid/d1-ultra":0.040724817640031497,"open/intern-decision-4b":0.11840617139815589,"open/robojev-27b-v1@0.5":0.00023419781177850732,"open/robojev-27b":null,"open/robojev-4b-v2":0.0007898659476910931,"open/robojev-4b-v3@0.25":0.01243165135383606,"open/robojev-4b-v3@0.5":0.001387383540264805,"open/robojev-4b-v3@0.75":0.000490768268226868,"open/robojev-4b-v3":0.00035794164692484856,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.030731146757701017,"respan/span-02":0.06529742,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.003364248178322421,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00360107421875}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000016","task":"Stack the colouful blocks on top of each other","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000016","predictions":{"RoboJev-27B":0.9957875625724997,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.9790242354083423,"TypeSafe Jev 1.14":0.9,"Perplexity Decider":0.9678616258735734,"Liquid D1":0.9964063968716766,"Mercury Decide":0.9971990724150798,"Cloudflare Clef":0.8405,"cloudflare/clef-flash":0.7532,"cloudflare/clef-omni":0.1605,"liquid/d1-ultra":0.9889278327569634,"open/intern-decision-4b":0.8815938286018441,"open/robojev-27b-v1@0.5":0.9826421366005592,"open/robojev-27b":null,"open/robojev-4b-v2":0.8330143331540432,"open/robojev-4b-v3@0.25":0.9924227595329285,"open/robojev-4b-v3@0.5":0.9960351551270282,"open/robojev-4b-v3@0.75":0.9960720983814959,"open/robojev-4b-v3":0.995415297724328,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9828393349370474,"respan/span-02":0.9401383,"typesafe/jev-1.13":0.92,"JEV-27B-VL (10 frames)":0.892126717767827,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.6484375}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000018","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000018","predictions":{"RoboJev-27B":0.003761559352175918,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.004214565723411135,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.01453179577742687,"Liquid D1":0.033085976958581766,"Mercury Decide":0.0029810330509460257,"Cloudflare Clef":0.0535,"cloudflare/clef-flash":0.1388,"cloudflare/clef-omni":0.0279,"liquid/d1-ultra":0.04917795241760473,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":0.0006075540887015197,"open/robojev-27b":null,"open/robojev-4b-v2":0.0006607800349070568,"open/robojev-4b-v3@0.25":0.01798621006309986,"open/robojev-4b-v3@0.5":0.002197092076271529,"open/robojev-4b-v3@0.75":0.00078986592964705,"open/robojev-4b-v3":0.0004958725302896432,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.03936307141050299,"respan/span-02":0.031146593,"typesafe/jev-1.13":0.03,"JEV-27B-VL (10 frames)":0.010657262976220813,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.007110595703125}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000019","task":"Stack the colouful blocks on top of each other","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000019","predictions":{"RoboJev-27B":0.23453383160265015,"GPT-6 Astra":0.78,"GPT-6.1 Sol":0.87,"Claude Opus 5.5":0.45,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.7267013048825145,"TypeSafe Jev 1.14":0.75,"Perplexity Decider":0.788009746927707,"Liquid D1":0.9933071493729063,"Mercury Decide":0.9669140187510509,"Cloudflare Clef":0.7237,"cloudflare/clef-flash":0.8602,"cloudflare/clef-omni":0.1877,"liquid/d1-ultra":0.7382047646338029,"open/intern-decision-4b":0.8748864949022742,"open/robojev-27b-v1@0.5":0.43882596808778856,"open/robojev-27b":null,"open/robojev-4b-v2":0.008730681628235537,"open/robojev-4b-v3@0.25":0.9740425944328308,"open/robojev-4b-v3@0.5":0.8290553898010261,"open/robojev-4b-v3@0.75":0.1107273107211166,"open/robojev-4b-v3":0.013473327870331066,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.9538335323400996,"respan/span-02":0.9627935,"typesafe/jev-1.13":0.61,"JEV-27B-VL (10 frames)":0.3930713704929715,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.267578125}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000020","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000020","predictions":{"RoboJev-27B":0.022434391554127756,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.026371601056166732,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.025777689667838943,"Liquid D1":0.05665242132616554,"Mercury Decide":0.0017007226675941401,"Cloudflare Clef":0.205,"cloudflare/clef-flash":0.2176,"cloudflare/clef-omni":0.1493,"liquid/d1-ultra":0.13865651085454225,"open/intern-decision-4b":0.608060011110835,"open/robojev-27b-v1@0.5":0.0033135803790118293,"open/robojev-27b":null,"open/robojev-4b-v2":0.006402505190256269,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.04343408155889982,"open/robojev-4b-v3@0.75":0.05133579603952293,"open/robojev-4b-v3":0.03326028532667912,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.13346241544529389,"respan/span-02":0.7845057,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.04854049951910218,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0029754638671875}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000022","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000022","predictions":{"RoboJev-27B":0.0020297121657479977,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0023787396194457854,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.013875915834578766,"Liquid D1":0.009125637759720109,"Mercury Decide":0.0009110513571608901,"Cloudflare Clef":0.0518,"cloudflare/clef-flash":0.132,"cloudflare/clef-omni":0.0317,"liquid/d1-ultra":0.03210338893543962,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.0003703781872593997,"open/robojev-27b":null,"open/robojev-4b-v2":0.0006319478692897959,"open/robojev-4b-v3@0.25":0.009708477184176445,"open/robojev-4b-v3@0.5":0.0012991606299284312,"open/robojev-4b-v3@0.75":0.0006607800017573367,"open/robojev-4b-v3":0.0004958725302896432,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.023406021419042057,"respan/span-02":0.037446465,"typesafe/jev-1.13":0.03,"JEV-27B-VL (10 frames)":0.0027927089825348214,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0023956298828125}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000023","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000023","predictions":{"RoboJev-27B":0.021227202907033286,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.07040458501505098,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.035019345760884626,"Liquid D1":0.04742587452393617,"Mercury Decide":0.008577484217809378,"Cloudflare Clef":0.1039,"cloudflare/clef-flash":0.1693,"cloudflare/clef-omni":0.0476,"liquid/d1-ultra":0.1328653285381552,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.001554918807904782,"open/robojev-27b":null,"open/robojev-4b-v2":0.0008635702282952242,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.005872534859081002,"open/robojev-4b-v3@0.75":0.0018155968873527504,"open/robojev-4b-v3":0.0008535800184851479,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1068835304000989,"respan/span-02":0.052288957,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.5703987796030744,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1279296875}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000024","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000024","predictions":{"RoboJev-27B":0.0012565041532898668,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0069341486160340755,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.02426813590164653,"Liquid D1":0.04468086836450484,"Mercury Decide":0.003376612739026561,"Cloudflare Clef":0.1844,"cloudflare/clef-flash":0.2005,"cloudflare/clef-omni":0.0482,"liquid/d1-ultra":0.07463357498887327,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":8.237866072694495e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.0009029603038478018,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.005872534859081002,"open/robojev-4b-v3@0.75":0.0013488637996850762,"open/robojev-4b-v3":0.0006506053076953617,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.08144227867727664,"respan/span-02":0.092879795,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.000507831551395948,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.018310546875}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000025","task":"Stack the colouful blocks on top of each other","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000025","predictions":{"RoboJev-27B":0.9960969877008067,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.96,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.994813789945351,"TypeSafe Jev 1.14":0.92,"Perplexity Decider":0.9909408070427123,"Liquid D1":0.9981897887954164,"Mercury Decide":0.9990889487886453,"Cloudflare Clef":0.9483,"cloudflare/clef-flash":0.9005,"cloudflare/clef-omni":0.1039,"liquid/d1-ultra":0.9908937465370646,"open/intern-decision-4b":0.8879876242264044,"open/robojev-27b-v1@0.5":0.9965584245965853,"open/robojev-27b":null,"open/robojev-4b-v2":0.13296424849235422,"open/robojev-4b-v3@0.25":0.9924227595329285,"open/robojev-4b-v3@0.5":0.9960351551270282,"open/robojev-4b-v3@0.75":0.9955777150142046,"open/robojev-4b-v3":0.9946077800781816,"openai/gpt-6-luna-decisions":0.99,"perplexity/pplx-decider-flash-v1.2":0.9876293070211067,"respan/span-02":0.9682492,"typesafe/jev-1.13":0.9,"JEV-27B-VL (10 frames)":0.8067589410401449,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.74609375}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000026","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000026","predictions":{"RoboJev-27B":0.003394957673505215,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.007095088559165199,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.043738721999524034,"Liquid D1":0.29421497216298875,"Mercury Decide":0.002631674145998697,"Cloudflare Clef":0.1664,"cloudflare/clef-flash":0.1916,"cloudflare/clef-omni":0.0276,"liquid/d1-ultra":0.1328653258261861,"open/intern-decision-4b":0.8184242551251981,"open/robojev-27b-v1@0.5":0.00034899216445941186,"open/robojev-27b":null,"open/robojev-4b-v2":0.005361080321059209,"open/robojev-4b-v3@0.25":0.2689414322376251,"open/robojev-4b-v3@0.5":0.008141294289513608,"open/robojev-4b-v3@0.75":0.0025929030441612317,"open/robojev-4b-v3":0.00106063530615271,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.11784420152588886,"respan/span-02":0.09105417,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.025834569174698587,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.004608154296875}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000027","task":"Stack the colouful blocks on top of each other","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000027","predictions":{"RoboJev-27B":0.004075803124756494,"GPT-6 Astra":0.005,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.004429979139640827,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.0326838807192261,"Liquid D1":0.22270013882530884,"Mercury Decide":0.01243165064737481,"Cloudflare Clef":0.2907,"cloudflare/clef-flash":0.4308,"cloudflare/clef-omni":0.0525,"liquid/d1-ultra":0.06809489885689386,"open/intern-decision-4b":0.11840617139815589,"open/robojev-27b-v1@0.5":0.00023715489758445958,"open/robojev-27b":null,"open/robojev-4b-v2":0.002751490629587489,"open/robojev-4b-v3@0.25":0.7057850360870361,"open/robojev-4b-v3@0.5":0.2715362708842343,"open/robojev-4b-v3@0.75":0.24398537221615502,"open/robojev-4b-v3":0.3303678724294036,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.07644908336021883,"respan/span-02":0.8185933,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.03784682092447923,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0225830078125}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000028","task":"Stack the colouful blocks on top of each other","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000028","predictions":{"RoboJev-27B":0.985770587546613,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.9812700221119562,"TypeSafe Jev 1.14":0.87,"Perplexity Decider":0.9698154245748085,"Liquid D1":0.9961755168663043,"Mercury Decide":0.9959298613270949,"Cloudflare Clef":0.8636,"cloudflare/clef-flash":0.8507,"cloudflare/clef-omni":0.0969,"liquid/d1-ultra":0.9781418579476889,"open/intern-decision-4b":0.8940776460411956,"open/robojev-27b-v1@0.5":0.995254524941913,"open/robojev-27b":null,"open/robojev-4b-v2":0.7772998717278379,"open/robojev-4b-v3@0.25":0.9924227595329285,"open/robojev-4b-v3@0.5":0.9948477587981382,"open/robojev-4b-v3@0.75":0.9936914684179292,"open/robojev-4b-v3":0.9925443850931952,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9830452836246101,"respan/span-02":0.94326466,"typesafe/jev-1.13":0.86,"JEV-27B-VL (10 frames)":0.7809611540824268,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.298828125}},{"suite":"so101","id":"block_stack/grootn1.7/eval_debug_task_cell_1_08h11m_29-jun-2026/ep000029","task":"Stack the colouful blocks on top of each other","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"block_stack","episode":"ep000029","predictions":{"RoboJev-27B":0.46550554627048485,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.7701251304015357,"TypeSafe Jev 1.14":0.66,"Perplexity Decider":0.7825227735353927,"Liquid D1":0.9706877690366521,"Mercury Decide":0.9770226295045603,"Cloudflare Clef":0.5055,"cloudflare/clef-flash":0.7014,"cloudflare/clef-omni":0.1899,"liquid/d1-ultra":0.6209651777561939,"open/intern-decision-4b":0.91062577829021,"open/robojev-27b-v1@0.5":0.5754592487533293,"open/robojev-27b":null,"open/robojev-4b-v2":0.031143833396690305,"open/robojev-4b-v3@0.25":0.970687747001648,"open/robojev-4b-v3@0.5":0.9442201868171092,"open/robojev-4b-v3@0.75":0.27840626377504696,"open/robojev-4b-v3":0.10211768392406631,"openai/gpt-6-luna-decisions":0.99,"perplexity/pplx-decider-flash-v1.2":0.8793682928683019,"respan/span-02":0.9307139,"typesafe/jev-1.13":0.59,"JEV-27B-VL (10 frames)":0.6288196673596433,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1435546875}},{"suite":"so101","id":"cable_clip/act/eval_debug_task_cell_3_14h57m_18-jun-2026/ep000000","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000000","predictions":{"RoboJev-27B":0.012296205755031677,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.016337251250490903,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.13877710373518085,"Liquid D1":0.06008664428307651,"Mercury Decide":0.008577483417901103,"Cloudflare Clef":0.2447,"cloudflare/clef-flash":0.1877,"cloudflare/clef-omni":0.0946,"liquid/d1-ultra":0.06809489997719319,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.0013317519783391499,"open/robojev-27b":null,"open/robojev-4b-v2":0.0015418730931173695,"open/robojev-4b-v3@0.25":0.03308597952127457,"open/robojev-4b-v3@0.5":0.0037133326112963453,"open/robojev-4b-v3@0.75":0.0014314726301544898,"open/robojev-4b-v3":0.0007252556958492492,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1219801716603912,"respan/span-02":0.064236276,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.05179707865655165,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00537109375}},{"suite":"so101","id":"cable_clip/act/eval_debug_task_cell_3_14h57m_18-jun-2026/ep000001","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000001","predictions":{"RoboJev-27B":0.008420527397349484,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.03143970593168371,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.08052077354646202,"Liquid D1":0.17328819739040088,"Mercury Decide":0.017986212067650338,"Cloudflare Clef":0.2463,"cloudflare/clef-flash":0.1891,"cloudflare/clef-omni":0.0925,"liquid/d1-ultra":0.21695809990668272,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.0016753493171279272,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016121527751335812,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.011276606158891207,"open/robojev-4b-v3@0.75":0.0037017607703716303,"open/robojev-4b-v3":0.0013178502752796797,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.128462877105617,"respan/span-02":0.08202085,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.03102607729029039,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00689697265625}},{"suite":"so101","id":"cable_clip/act/eval_debug_task_cell_3_14h57m_18-jun-2026/ep000007","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000007","predictions":{"RoboJev-27B":0.003936681261213534,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.00895708313587258,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.020573330208876854,"Liquid D1":0.05665242849342066,"Mercury Decide":0.0010987312896201993,"Cloudflare Clef":0.3219,"cloudflare/clef-flash":0.2249,"cloudflare/clef-omni":0.117,"liquid/d1-ultra":0.19285323075809116,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.0009853200586606946,"open/robojev-27b":null,"open/robojev-4b-v2":0.001410358480093293,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.004825770646864498,"open/robojev-4b-v3@0.75":0.0015191329853098835,"open/robojev-4b-v3":0.0007252556958492492,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.11392276915656077,"respan/span-02":0.04937301,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.006578783937970071,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00885009765625}},{"suite":"so101","id":"cable_clip/act/eval_debug_task_cell_3_14h57m_18-jun-2026/ep000008","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000008","predictions":{"RoboJev-27B":0.005717024332513544,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.00795712737335787,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.01958667871667286,"Liquid D1":0.14804719427274565,"Mercury Decide":0.000911051029945011,"Cloudflare Clef":0.2653,"cloudflare/clef-flash":0.2108,"cloudflare/clef-omni":0.117,"liquid/d1-ultra":0.16396261608449783,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.0006558070369261324,"open/robojev-27b":null,"open/robojev-4b-v2":0.0012900470555811355,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.0032570072049156237,"open/robojev-4b-v3@0.75":0.0008896347161823813,"open/robojev-4b-v3":0.00035794164692484856,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.12459149576820762,"respan/span-02":0.03707889,"typesafe/jev-1.13":0.09,"JEV-27B-VL (10 frames)":0.03845049070563442,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0047607421875}},{"suite":"so101","id":"cable_clip/diffusion/eval_debug_task_cell_3_16h48m_18-jun-2026/ep000002","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000002","predictions":{"RoboJev-27B":0.004795004208657464,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.02627289932403992,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.049583786964298215,"Liquid D1":0.16451645880021026,"Mercury Decide":0.009708475899467857,"Cloudflare Clef":0.3281,"cloudflare/clef-flash":0.247,"cloudflare/clef-omni":0.1103,"liquid/d1-ultra":0.19285321976582573,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.0007765370102679114,"open/robojev-27b":null,"open/robojev-4b-v2":0.0031445701339940513,"open/robojev-4b-v3@0.25":0.07585817575454712,"open/robojev-4b-v3@0.5":0.008141294289513608,"open/robojev-4b-v3@0.75":0.0023025600819802016,"open/robojev-4b-v3":0.0007252556958492492,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3024512383727666,"respan/span-02":0.11854963,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.23739162055469076,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00860595703125}},{"suite":"so101","id":"cable_clip/diffusion/eval_debug_task_cell_3_16h48m_18-jun-2026/ep000003","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000003","predictions":{"RoboJev-27B":0.006450513240677073,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0119207938538615,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.03630993223879249,"Liquid D1":0.06371499158516146,"Mercury Decide":0.020332351487562173,"Cloudflare Clef":0.262,"cloudflare/clef-flash":0.1987,"cloudflare/clef-omni":0.0862,"liquid/d1-ultra":0.18528536249391386,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.00028476910085833046,"open/robojev-27b":null,"open/robojev-4b-v2":0.0011799866576912997,"open/robojev-4b-v3@0.25":0.02595735713839531,"open/robojev-4b-v3@0.5":0.004233320503182646,"open/robojev-4b-v3@0.75":0.0015191329853098835,"open/robojev-4b-v3":0.0006869178295131179,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.16334753666214036,"respan/span-02":0.057036508,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.07589591812180305,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.007568359375}},{"suite":"so101","id":"cable_clip/diffusion/eval_debug_task_cell_3_16h48m_18-jun-2026/ep000006","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000006","predictions":{"RoboJev-27B":0.008313608556525858,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.010593512437520838,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.03868940233607365,"Liquid D1":0.0850990519679964,"Mercury Decide":0.005220126660807012,"Cloudflare Clef":0.2796,"cloudflare/clef-flash":0.1482,"cloudflare/clef-omni":0.0968,"liquid/d1-ultra":0.18528536249391386,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.0003869217579762906,"open/robojev-27b":null,"open/robojev-4b-v2":0.001410358480093293,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.003964844872971652,"open/robojev-4b-v3@0.75":0.0015191329853098835,"open/robojev-4b-v3":0.0004958725302896432,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.19332801996820853,"respan/span-02":0.08788301,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.0746576310513918,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.007110595703125}},{"suite":"so101","id":"cable_clip/diffusion/eval_debug_task_cell_3_16h48m_18-jun-2026/ep000007","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000007","predictions":{"RoboJev-27B":0.004861979673582417,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.008888970956159628,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.018648808777447814,"Liquid D1":0.03732688627322502,"Mercury Decide":0.01098694125427802,"Cloudflare Clef":0.2581,"cloudflare/clef-flash":0.1732,"cloudflare/clef-omni":0.1006,"liquid/d1-ultra":0.11671092886460685,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.0001820933060323336,"open/robojev-27b":null,"open/robojev-4b-v2":0.0011285254845784295,"open/robojev-4b-v3@0.25":0.022977370768785477,"open/robojev-4b-v3@0.5":0.003964844872971652,"open/robojev-4b-v3@0.75":0.001271016248975737,"open/robojev-4b-v3":0.0005235534182684861,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1374130525953955,"respan/span-02":0.070569105,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.024450403686881582,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00860595703125}},{"suite":"so101","id":"cable_clip/diffusion/eval_debug_task_cell_3_16h48m_18-jun-2026/ep000009","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000009","predictions":{"RoboJev-27B":0.01681934167076595,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.03914606192793486,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.08180347115981457,"Liquid D1":0.08035747542939525,"Mercury Decide":0.03732689055684297,"Cloudflare Clef":0.2646,"cloudflare/clef-flash":0.211,"cloudflare/clef-omni":0.074,"liquid/d1-ultra":0.42648958363704076,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.002997281058072197,"open/robojev-27b":null,"open/robojev-4b-v2":0.006996270681650968,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.011276606158891207,"open/robojev-4b-v3@0.75":0.00204466165068541,"open/robojev-4b-v3":0.000583634235945364,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3239886701850221,"respan/span-02":0.041244734,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.09918195653059474,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01324462890625}},{"suite":"so101","id":"cable_clip/diffusion/eval_debug_task_cell_3_16h48m_18-jun-2026/ep000010","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000010","predictions":{"RoboJev-27B":0.07874174258914722,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.1396778797539674,"TypeSafe Jev 1.14":0.14,"Perplexity Decider":0.13081177327258556,"Liquid D1":0.2942149845400438,"Mercury Decide":0.08509904790742691,"Cloudflare Clef":0.3647,"cloudflare/clef-flash":0.2166,"cloudflare/clef-omni":0.1671,"liquid/d1-ultra":0.3674872706667976,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.003289976339430694,"open/robojev-27b":null,"open/robojev-4b-v2":0.002106299096066607,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.008690106319066306,"open/robojev-4b-v3@0.75":0.00244343308696661,"open/robojev-4b-v3":0.0009514973249264055,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.25220935844283576,"respan/span-02":0.08987761,"typesafe/jev-1.13":0.32,"JEV-27B-VL (10 frames)":0.2948639550340096,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0179443359375}},{"suite":"so101","id":"cable_clip/diffusion/eval_debug_task_cell_3_16h48m_18-jun-2026/ep000011","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000011","predictions":{"RoboJev-27B":0.006244069042277984,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.1036912514527361,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.16665858290627145,"Liquid D1":0.2689414213699951,"Mercury Decide":0.04742587788985982,"Cloudflare Clef":0.3782,"cloudflare/clef-flash":0.2423,"cloudflare/clef-omni":0.1621,"liquid/d1-ultra":0.2169580959077197,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.00716660109315468,"open/robojev-27b":null,"open/robojev-4b-v2":0.002751490629587489,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.0016121526329810115,"open/robojev-4b-v3":0.0005527786044704864,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.20203130025556304,"respan/span-02":0.07036696,"typesafe/jev-1.13":0.3,"JEV-27B-VL (10 frames)":0.027823456675355455,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0203857421875}},{"suite":"so101","id":"cable_clip/smolvla/eval_debug_task_cell_3_10h15m_26-jun-2026/ep000002","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000002","predictions":{"RoboJev-27B":0.006230821380613649,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.035285699372545366,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.09236235625197824,"Liquid D1":0.07585817793199003,"Mercury Decide":0.02595735616172174,"Cloudflare Clef":0.3126,"cloudflare/clef-flash":0.2019,"cloudflare/clef-omni":0.1135,"liquid/d1-ultra":0.13286531633429452,"open/intern-decision-4b":0.1395062328236417,"open/robojev-27b-v1@0.5":0.0018586857786901752,"open/robojev-27b":null,"open/robojev-4b-v2":0.0007554056122179476,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.005872534859081002,"open/robojev-4b-v3@0.75":0.00204466165068541,"open/robojev-4b-v3":0.0007657313877976473,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1412664334237927,"respan/span-02":0.094829686,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.030657848437607542,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00860595703125}},{"suite":"so101","id":"cable_clip/smolvla/eval_debug_task_cell_3_10h15m_26-jun-2026/ep000008","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000008","predictions":{"RoboJev-27B":0.003469621284718847,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.003335125729687539,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.016784789510457594,"Liquid D1":0.19193279106941588,"Mercury Decide":0.0004583129330597952,"Cloudflare Clef":0.1858,"cloudflare/clef-flash":0.2441,"cloudflare/clef-omni":0.1216,"liquid/d1-ultra":0.10691173740296395,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.00039322314406837,"open/robojev-27b":null,"open/robojev-4b-v2":0.0017624512139676404,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.0037133326112963453,"open/robojev-4b-v3@0.75":0.0010633807184710219,"open/robojev-4b-v3":0.0004958725302896432,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.10883594464931798,"respan/span-02":0.06397811,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.0120049945638539,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00628662109375}},{"suite":"so101","id":"cable_clip/smolvla/eval_debug_task_cell_3_10h15m_26-jun-2026/ep000011","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000011","predictions":{"RoboJev-27B":0.00719579830864212,"GPT-6 Astra":0.06,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.01609153332827998,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.03441776485600899,"Liquid D1":0.5621765008857981,"Mercury Decide":0.003824483552383861,"Cloudflare Clef":0.3838,"cloudflare/clef-flash":0.3298,"cloudflare/clef-omni":0.1881,"liquid/d1-ultra":0.2341987426829336,"open/intern-decision-4b":0.36247442200877295,"open/robojev-27b-v1@0.5":0.0013128322556610172,"open/robojev-27b":null,"open/robojev-4b-v2":0.0012900470555811355,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.006692850574775813,"open/robojev-4b-v3@0.75":0.0017108587429636138,"open/robojev-4b-v3":0.0006506053076953617,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.33139628391998593,"respan/span-02":0.077262715,"typesafe/jev-1.13":0.18,"JEV-27B-VL (10 frames)":0.13316647507574883,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0057373046875}},{"suite":"so101","id":"cable_clip/smolvla/eval_debug_task_cell_3_10h15m_26-jun-2026/ep000012","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000012","predictions":{"RoboJev-27B":0.004360728734781721,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.0035463428853598614,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.02327222167586231,"Liquid D1":0.17328821019878954,"Mercury Decide":0.0005527785690055587,"Cloudflare Clef":0.2319,"cloudflare/clef-flash":0.212,"cloudflare/clef-omni":0.1144,"liquid/d1-ultra":0.2431681531083896,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.00022510521938069026,"open/robojev-27b":null,"open/robojev-4b-v2":0.0014746525778226533,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.004519892642389456,"open/robojev-4b-v3@0.75":0.0016121526329810115,"open/robojev-4b-v3":0.0008084643262252317,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.11158747285761736,"respan/span-02":0.05926361,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.018917782138961593,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.005218505859375}},{"suite":"so101","id":"cable_clip/smolvla/eval_debug_task_cell_3_10h15m_26-jun-2026/ep000014","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000014","predictions":{"RoboJev-27B":0.005991448810675907,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.028423068312998366,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.07286676399339453,"Liquid D1":0.07585818628900447,"Mercury Decide":0.020332351153644804,"Cloudflare Clef":0.298,"cloudflare/clef-flash":0.1809,"cloudflare/clef-omni":0.1292,"liquid/d1-ultra":0.23419873846123568,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.0007059539730152946,"open/robojev-27b":null,"open/robojev-4b-v2":0.0011285254845784295,"open/robojev-4b-v3@0.25":0.03308597952127457,"open/robojev-4b-v3@0.5":0.004233320503182646,"open/robojev-4b-v3@0.75":0.0011976561657233782,"open/robojev-4b-v3":0.0005235534182684861,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.20666879770528424,"respan/span-02":0.07550367,"typesafe/jev-1.13":0.13,"JEV-27B-VL (10 frames)":0.046107699386425664,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.010009765625}},{"suite":"so101","id":"cable_clip/smolvla/eval_debug_task_cell_3_10h15m_26-jun-2026/ep000016","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000016","predictions":{"RoboJev-27B":0.015553779038306988,"GPT-6 Astra":0.83,"GPT-6.1 Sol":0.78,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.18790752028515795,"TypeSafe Jev 1.14":0.22,"Perplexity Decider":0.07795818539138069,"Liquid D1":0.37754066879814546,"Mercury Decide":0.015906394889894166,"Cloudflare Clef":0.3067,"cloudflare/clef-flash":0.272,"cloudflare/clef-omni":0.165,"liquid/d1-ultra":0.5123386675987678,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.003465319567299237,"open/robojev-27b":null,"open/robojev-4b-v2":0.004905405551811006,"open/robojev-4b-v3@0.25":0.18242551386356354,"open/robojev-4b-v3@0.5":0.022977370307335907,"open/robojev-4b-v3@0.75":0.005604465074944334,"open/robojev-4b-v3":0.0013178502752796797,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3040227063061372,"respan/span-02":0.08419211,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.1177836858759005,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.016357421875}},{"suite":"so101","id":"cable_clip/smolvla/eval_debug_task_cell_3_10h15m_26-jun-2026/ep000020","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000020","predictions":{"RoboJev-27B":0.05273183179883679,"GPT-6 Astra":0.8,"GPT-6.1 Sol":0.78,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.35411224581695666,"TypeSafe Jev 1.14":0.19,"Perplexity Decider":0.28440381485074595,"Liquid D1":0.46879062662624377,"Mercury Decide":0.3208213138121609,"Cloudflare Clef":0.278,"cloudflare/clef-flash":0.205,"cloudflare/clef-omni":0.1439,"liquid/d1-ultra":0.450795090135065,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.05779880572043028,"open/robojev-27b":null,"open/robojev-4b-v2":0.005858834000676852,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.011276606158891207,"open/robojev-4b-v3@0.75":0.0025929030441612317,"open/robojev-4b-v3":0.0007252556958492492,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.2797865972292746,"respan/span-02":0.049981795,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.17049886933098957,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01495361328125}},{"suite":"so101","id":"cable_clip/smolvla/eval_debug_task_cell_3_10h15m_26-jun-2026/ep000023","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000023","predictions":{"RoboJev-27B":0.0042854026564193145,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.008754277516962691,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.014463266544638038,"Liquid D1":0.2689414096510108,"Mercury Decide":0.0059110687194295275,"Cloudflare Clef":0.1262,"cloudflare/clef-flash":0.1565,"cloudflare/clef-omni":0.0932,"liquid/d1-ultra":0.13865650804326832,"open/intern-decision-4b":0.1395062328236417,"open/robojev-27b-v1@0.5":0.0005180117203897975,"open/robojev-27b":null,"open/robojev-4b-v2":0.000825897021041206,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.006269376036423619,"open/robojev-4b-v3@0.75":0.0013488637996850762,"open/robojev-4b-v3":0.0004696544949846406,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1241288959021668,"respan/span-02":0.07224287,"typesafe/jev-1.13":0.18,"JEV-27B-VL (10 frames)":0.12162159607993489,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0194091796875}},{"suite":"so101","id":"cable_clip/smolvla/eval_debug_task_cell_3_10h15m_26-jun-2026/ep000025","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_clip","episode":"ep000025","predictions":{"RoboJev-27B":0.003619837140562092,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.008720922174091386,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.0185221556901835,"Liquid D1":0.11920292828022305,"Mercury Decide":0.003593602954915036,"Cloudflare Clef":0.2681,"cloudflare/clef-flash":0.2129,"cloudflare/clef-omni":0.1354,"liquid/d1-ultra":0.09357238381149649,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.0003561871121443429,"open/robojev-27b":null,"open/robojev-4b-v2":0.001348863876427256,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.001271016248975737,"open/robojev-4b-v3":0.0006506053076953617,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1679093312531262,"respan/span-02":0.115231246,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.1512396089421623,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006103515625}},{"suite":"so101","id":"cable_unclip/act/eval_debug_task_cell_3_15h36m_26-jun-2026/ep000002","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000002","predictions":{"RoboJev-27B":0.8970343978789513,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.62,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.6006042424660509,"TypeSafe Jev 1.14":0.43,"Perplexity Decider":0.352657106527847,"Liquid D1":0.7981867825403176,"Mercury Decide":0.924141814233309,"Cloudflare Clef":0.5489,"cloudflare/clef-flash":0.2732,"cloudflare/clef-omni":0.1714,"liquid/d1-ultra":0.21695809590771967,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.8463986094533383,"open/robojev-27b":null,"open/robojev-4b-v2":0.0893637337766288,"open/robojev-4b-v3@0.25":0.8354835510253906,"open/robojev-4b-v3@0.5":0.45081746874907896,"open/robojev-4b-v3@0.75":0.7668262163944938,"open/robojev-4b-v3":0.7579190349557637,"openai/gpt-6-luna-decisions":0.1,"perplexity/pplx-decider-flash-v1.2":0.34974005100436895,"respan/span-02":0.10992878,"typesafe/jev-1.13":0.35,"JEV-27B-VL (10 frames)":0.6246821874935748,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01495361328125}},{"suite":"so101","id":"cable_unclip/act/eval_debug_task_cell_3_15h36m_26-jun-2026/ep000007","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000007","predictions":{"RoboJev-27B":0.9593234946497315,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.7886570421869483,"TypeSafe Jev 1.14":0.66,"Perplexity Decider":0.6863931448747834,"Liquid D1":0.4378234991142019,"Mercury Decide":0.9579122705824801,"Cloudflare Clef":0.4428,"cloudflare/clef-flash":0.2385,"cloudflare/clef-omni":0.1896,"liquid/d1-ultra":0.24316814444430646,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.9568022915551683,"open/robojev-27b":null,"open/robojev-4b-v2":0.03700737584165394,"open/robojev-4b-v3@0.25":0.622459352016449,"open/robojev-4b-v3@0.5":0.4184967522309292,"open/robojev-4b-v3@0.75":0.6713474489845783,"open/robojev-4b-v3":0.6451587915501215,"openai/gpt-6-luna-decisions":0.1,"perplexity/pplx-decider-flash-v1.2":0.6169705389426062,"respan/span-02":0.096936636,"typesafe/jev-1.13":0.58,"JEV-27B-VL (10 frames)":0.6588244140684976,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.255859375}},{"suite":"so101","id":"cable_unclip/act/eval_debug_task_cell_3_15h36m_26-jun-2026/ep000015","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000015","predictions":{"RoboJev-27B":0.9669151813679588,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.75,"JEV-27B-VL":0.8279295038886101,"TypeSafe Jev 1.14":0.66,"Perplexity Decider":0.7780155925929372,"Liquid D1":0.817574471748733,"Mercury Decide":0.985936373602433,"Cloudflare Clef":0.4922,"cloudflare/clef-flash":0.2989,"cloudflare/clef-omni":0.1405,"liquid/d1-ultra":0.6325127183904116,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.9762493446229819,"open/robojev-27b":null,"open/robojev-4b-v2":0.03700737584165394,"open/robojev-4b-v3@0.25":0.2689414322376251,"open/robojev-4b-v3@0.5":0.1368024864039654,"open/robojev-4b-v3@0.75":0.1107273107211166,"open/robojev-4b-v3":0.08810813794451551,"openai/gpt-6-luna-decisions":0.08,"perplexity/pplx-decider-flash-v1.2":0.3588435232638507,"respan/span-02":0.114369296,"typesafe/jev-1.13":0.53,"JEV-27B-VL (10 frames)":0.8134842370664671,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.302734375}},{"suite":"so101","id":"cable_unclip/act/eval_debug_task_cell_3_15h36m_26-jun-2026/ep000018","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000018","predictions":{"RoboJev-27B":0.05311005549991199,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.01609153332827998,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.028820961236370603,"Liquid D1":0.2942149845400438,"Mercury Decide":0.004070137504485895,"Cloudflare Clef":0.2983,"cloudflare/clef-flash":0.2051,"cloudflare/clef-omni":0.1905,"liquid/d1-ultra":0.15730751772911566,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.004910435534328859,"open/robojev-27b":null,"open/robojev-4b-v2":0.07278720919427024,"open/robojev-4b-v3@0.25":0.07585817575454712,"open/robojev-4b-v3@0.5":0.027851233668696997,"open/robojev-4b-v3@0.75":0.02297736967873775,"open/robojev-4b-v3":0.02297737029287157,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.11176306567218751,"respan/span-02":0.0586389,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.6659302996561791,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0113525390625}},{"suite":"so101","id":"cable_unclip/act/eval_debug_task_cell_3_15h36m_26-jun-2026/ep000023","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000023","predictions":{"RoboJev-27B":0.8194695145928904,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.41976681585764625,"TypeSafe Jev 1.14":0.31,"Perplexity Decider":0.16404589109495674,"Liquid D1":0.9241418126663687,"Mercury Decide":0.2942149845400438,"Cloudflare Clef":0.3811,"cloudflare/clef-flash":0.2206,"cloudflare/clef-omni":0.1692,"liquid/d1-ultra":0.34485307864473513,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.5933742399173533,"open/robojev-27b":null,"open/robojev-4b-v2":0.8817313360707654,"open/robojev-4b-v3@0.25":0.531209409236908,"open/robojev-4b-v3@0.5":0.34121268247291503,"open/robojev-4b-v3@0.75":0.3419172570227415,"open/robojev-4b-v3":0.3303678724294036,"openai/gpt-6-luna-decisions":0.06,"perplexity/pplx-decider-flash-v1.2":0.3385649474777134,"respan/span-02":0.11806139,"typesafe/jev-1.13":0.21,"JEV-27B-VL (10 frames)":0.5888578545973207,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0091552734375}},{"suite":"so101","id":"cable_unclip/act/eval_debug_task_cell_3_15h36m_26-jun-2026/ep000029","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000029","predictions":{"RoboJev-27B":0.06370377958231076,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.11414986565966936,"TypeSafe Jev 1.14":0.39,"Perplexity Decider":0.11265056693953755,"Liquid D1":0.23370635691404026,"Mercury Decide":0.06008664638698042,"Cloudflare Clef":0.2407,"cloudflare/clef-flash":0.2171,"cloudflare/clef-omni":0.1126,"liquid/d1-ultra":0.1272802666282991,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":0.1819189425647764,"open/robojev-27b":null,"open/robojev-4b-v2":0.08235931880879026,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.07137286741841814,"open/robojev-4b-v3@0.75":0.1754304037756096,"open/robojev-4b-v3":0.2625786543234272,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.28926777044004476,"respan/span-02":0.0670335,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.22229291806234225,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00885009765625}},{"suite":"so101","id":"cable_unclip/diffusion/eval_debug_task_cell_3_09h08m_24-jun-2026/ep000000","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000000","predictions":{"RoboJev-27B":0.026312195208962493,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.31305701944092784,"TypeSafe Jev 1.14":0.18,"Perplexity Decider":0.06619234691199735,"Liquid D1":0.37754066879814546,"Mercury Decide":0.053403329799824234,"Cloudflare Clef":0.346,"cloudflare/clef-flash":0.299,"cloudflare/clef-omni":0.1679,"liquid/d1-ultra":0.18528535183398262,"open/intern-decision-4b":0.3201997500236374,"open/robojev-27b-v1@0.5":0.04293618458215513,"open/robojev-27b":null,"open/robojev-4b-v2":0.03544887275269872,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.10858632498619036,"open/robojev-4b-v3@0.75":0.05133579603952293,"open/robojev-4b-v3":0.047919347698515906,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.31907186157605444,"respan/span-02":0.12766112,"typesafe/jev-1.13":0.15,"JEV-27B-VL (10 frames)":0.0570956646124442,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0233154296875}},{"suite":"so101","id":"cable_unclip/diffusion/eval_debug_task_cell_3_09h08m_24-jun-2026/ep000002","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000002","predictions":{"RoboJev-27B":0.025307264431349993,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.00413451998864555,"TypeSafe Jev 1.14":0.24,"Perplexity Decider":0.020316658926314804,"Liquid D1":0.23370635691404026,"Mercury Decide":0.002631673405319097,"Cloudflare Clef":0.3556,"cloudflare/clef-flash":0.2656,"cloudflare/clef-omni":0.15,"liquid/d1-ultra":0.10228896652269512,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.0024590698369782817,"open/robojev-27b":null,"open/robojev-4b-v2":0.013576916891431232,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.010566189227213266,"open/robojev-4b-v3@0.75":0.008476838215708002,"open/robojev-4b-v3":0.006341061537493235,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.20843355719788367,"respan/span-02":0.10002858,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.14867286066683572,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006103515625}},{"suite":"so101","id":"cable_unclip/diffusion/eval_debug_task_cell_3_09h08m_24-jun-2026/ep000009","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000009","predictions":{"RoboJev-27B":0.884694497400339,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.7,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.7912132188180229,"TypeSafe Jev 1.14":0.34,"Perplexity Decider":0.371146088750718,"Liquid D1":0.8670357460591569,"Mercury Decide":0.9399133536130195,"Cloudflare Clef":0.4264,"cloudflare/clef-flash":0.2258,"cloudflare/clef-omni":0.237,"liquid/d1-ultra":0.25236786828046404,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.8429245349148431,"open/robojev-27b":null,"open/robojev-4b-v2":0.13296424849235422,"open/robojev-4b-v3@0.25":0.6513549089431763,"open/robojev-4b-v3@0.5":0.7992444628236429,"open/robojev-4b-v3@0.75":0.8411309059812064,"open/robojev-4b-v3":0.8362291906116784,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.35551788348846053,"respan/span-02":0.0871821,"typesafe/jev-1.13":0.37,"JEV-27B-VL (10 frames)":0.7548328719334277,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.44140625}},{"suite":"so101","id":"cable_unclip/diffusion/eval_debug_task_cell_3_09h36m_24-jun-2026/ep000000","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000000","predictions":{"RoboJev-27B":0.04675759457234365,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.27627437873606614,"TypeSafe Jev 1.14":0.13,"Perplexity Decider":0.07673560865562404,"Liquid D1":0.23370634623958197,"Mercury Decide":0.0330859768394049,"Cloudflare Clef":0.3187,"cloudflare/clef-flash":0.28,"cloudflare/clef-omni":0.1364,"liquid/d1-ultra":0.10691174189803228,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.07746200555125315,"open/robojev-27b":null,"open/robojev-4b-v2":0.059086031855120416,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.03593407330933149,"open/robojev-4b-v3@0.75":0.027346787282274982,"open/robojev-4b-v3":0.038921036473713755,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.24929836238353859,"respan/span-02":0.22648588,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.07218744215135453,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.04736328125}},{"suite":"so101","id":"cable_unclip/diffusion/eval_debug_task_cell_3_09h36m_24-jun-2026/ep000002","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000002","predictions":{"RoboJev-27B":0.08024805624797231,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.010756190704465202,"TypeSafe Jev 1.14":0.22,"Perplexity Decider":0.039416748520944664,"Liquid D1":0.12592275499444552,"Mercury Decide":0.004609571828971023,"Cloudflare Clef":0.3371,"cloudflare/clef-flash":0.2624,"cloudflare/clef-omni":0.1313,"liquid/d1-ultra":0.11171743294569182,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.0164326952873929,"open/robojev-27b":null,"open/robojev-4b-v2":0.059086031855120416,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.02154587702420825,"open/robojev-4b-v3@0.75":0.020451257661610673,"open/robojev-4b-v3":0.03155642361885442,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.33575973134139214,"respan/span-02":0.077233896,"typesafe/jev-1.13":0.12,"JEV-27B-VL (10 frames)":0.1365155737431551,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.004608154296875}},{"suite":"so101","id":"cable_unclip/diffusion/eval_debug_task_cell_3_09h36m_24-jun-2026/ep000007","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000007","predictions":{"RoboJev-27B":0.06026436270863326,"GPT-6 Astra":0.06,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.07193196445218132,"TypeSafe Jev 1.14":0.37,"Perplexity Decider":0.04200648404753767,"Liquid D1":0.4378234991142019,"Mercury Decide":0.014063627998849772,"Cloudflare Clef":0.2785,"cloudflare/clef-flash":0.2194,"cloudflare/clef-omni":0.1306,"liquid/d1-ultra":0.21695809590771967,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.04164523659153747,"open/robojev-27b":null,"open/robojev-4b-v2":0.03700737584165394,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.03828411009766295,"open/robojev-4b-v3@0.75":0.02435227726532882,"open/robojev-4b-v3":0.021788411170123766,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.1874571237120067,"respan/span-02":0.06978242,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.5883852404161528,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0174560546875}},{"suite":"so101","id":"cable_unclip/diffusion/eval_debug_task_cell_3_09h36m_24-jun-2026/ep000012","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000012","predictions":{"RoboJev-27B":0.020073233092799507,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.03387171146567607,"TypeSafe Jev 1.14":0.19,"Perplexity Decider":0.03250827126243325,"Liquid D1":0.1259227681153614,"Mercury Decide":0.005220124866560973,"Cloudflare Clef":0.3502,"cloudflare/clef-flash":0.2129,"cloudflare/clef-omni":0.2053,"liquid/d1-ultra":0.13865650242072058,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.015263550109190213,"open/robojev-27b":null,"open/robojev-4b-v2":0.054313267386278195,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.02450159025746704,"open/robojev-4b-v3@0.75":0.012071514031475902,"open/robojev-4b-v3":0.01146957225399579,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.17431746892964972,"respan/span-02":0.08363714,"typesafe/jev-1.13":0.09,"JEV-27B-VL (10 frames)":0.14439275670327384,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0128173828125}},{"suite":"so101","id":"cable_unclip/grootn1.7/eval_debug_task_cell_3_12h33m_27-jun-2026/ep000000","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000000","predictions":{"RoboJev-27B":0.07712127815024485,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.9,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.08233459056199974,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.029497312489897003,"Liquid D1":0.10669059394565118,"Mercury Decide":0.0066928514134122095,"Cloudflare Clef":0.281,"cloudflare/clef-flash":0.1814,"cloudflare/clef-omni":0.1132,"liquid/d1-ultra":0.11171743294569188,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":0.0074398162501699144,"open/robojev-27b":null,"open/robojev-4b-v2":0.04990557889898353,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.01664357488299338,"open/robojev-4b-v3@0.75":0.018197691623827453,"open/robojev-4b-v3":0.021788411170123766,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.27602434767651335,"respan/span-02":0.06714058,"typesafe/jev-1.13":0.18,"JEV-27B-VL (10 frames)":0.3027092424839642,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0128173828125}},{"suite":"so101","id":"cable_unclip/grootn1.7/eval_debug_task_cell_3_12h33m_27-jun-2026/ep000010","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000010","predictions":{"RoboJev-27B":0.6434432520750019,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":0.29513140224998224,"TypeSafe Jev 1.14":0.21,"Perplexity Decider":0.10392154178484979,"Liquid D1":0.3775406828054583,"Mercury Decide":0.0758581784543034,"Cloudflare Clef":0.4131,"cloudflare/clef-flash":0.2304,"cloudflare/clef-omni":0.178,"liquid/d1-ultra":0.1639626225378753,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.12544468597408917,"open/robojev-27b":null,"open/robojev-4b-v2":0.016188347137528064,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.03593407330933149,"open/robojev-4b-v3@0.75":0.019292242704938834,"open/robojev-4b-v3":0.018571313779720225,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.21611782410123725,"respan/span-02":0.16369674,"typesafe/jev-1.13":0.15,"JEV-27B-VL (10 frames)":0.3370909135504458,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.029296875}},{"suite":"so101","id":"cable_unclip/molmoact2/eval_cable_unclip_15h42m_08-jul-2026/ep000008","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000008","predictions":{"RoboJev-27B":0.8279934780542701,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.92,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.35,"JEV-27B-VL":0.3163793090345333,"TypeSafe Jev 1.14":0.3,"Perplexity Decider":0.14443793619270606,"Liquid D1":0.4073334000459302,"Mercury Decide":0.2689414096510108,"Cloudflare Clef":0.46,"cloudflare/clef-flash":0.194,"cloudflare/clef-omni":0.1842,"liquid/d1-ultra":0.21695808790979368,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.1932251723333176,"open/robojev-27b":null,"open/robojev-4b-v2":0.12300397797247992,"open/robojev-4b-v3@0.25":0.13296423852443695,"open/robojev-4b-v3@0.5":0.1447586588133107,"open/robojev-4b-v3@0.75":0.1754304037756096,"open/robojev-4b-v3":0.3303678724294036,"openai/gpt-6-luna-decisions":0.11,"perplexity/pplx-decider-flash-v1.2":0.29513805340069865,"respan/span-02":0.12878321,"typesafe/jev-1.13":0.36,"JEV-27B-VL (10 frames)":0.5001417964046744,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.044677734375}},{"suite":"so101","id":"cable_unclip/molmoact2/eval_cable_unclip_15h42m_08-jul-2026/ep000010","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000010","predictions":{"RoboJev-27B":0.269307450549706,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.41789200243302316,"TypeSafe Jev 1.14":0.41,"Perplexity Decider":0.22589545761013607,"Liquid D1":0.4073334000459302,"Mercury Decide":0.22270013882530884,"Cloudflare Clef":0.3709,"cloudflare/clef-flash":0.139,"cloudflare/clef-omni":0.1526,"liquid/d1-ultra":0.2914061599917239,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.36606987718924516,"open/robojev-27b":null,"open/robojev-4b-v2":0.0893637337766288,"open/robojev-4b-v3@0.25":0.7549149990081787,"open/robojev-4b-v3@0.5":0.846904551172507,"open/robojev-4b-v3@0.75":0.8411309059812064,"open/robojev-4b-v3":0.863871653255755,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.50235913433358,"respan/span-02":0.12948075,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.4206106741087692,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.015869140625}},{"suite":"so101","id":"cable_unclip/molmoact2/eval_cable_unclip_15h42m_08-jul-2026/ep000013","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000013","predictions":{"RoboJev-27B":0.8036402805503987,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.45004357313423854,"TypeSafe Jev 1.14":0.39,"Perplexity Decider":0.23722829204492837,"Liquid D1":0.8175744806385543,"Mercury Decide":0.11920292045759123,"Cloudflare Clef":0.3544,"cloudflare/clef-flash":0.1972,"cloudflare/clef-omni":0.1714,"liquid/d1-ultra":0.13865651507145324,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.6175672626201112,"open/robojev-27b":null,"open/robojev-4b-v2":0.16086775395337108,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.07137286741841814,"open/robojev-4b-v3@0.75":0.0717892678456694,"open/robojev-4b-v3":0.07585818271507015,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.42380940669556844,"respan/span-02":0.12777586,"typesafe/jev-1.13":0.34,"JEV-27B-VL (10 frames)":0.6493151234893372,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01165771484375}},{"suite":"so101","id":"cable_unclip/molmoact2/eval_cable_unclip_15h58m_08-jul-2026/ep000004","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000004","predictions":{"RoboJev-27B":0.9552435611641307,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.45,"Claude Sonnet 5.5":0.7,"JEV-27B-VL":0.5744796409805425,"TypeSafe Jev 1.14":0.48,"Perplexity Decider":0.28506350219900106,"Liquid D1":0.6791787121629466,"Mercury Decide":0.7772998611746911,"Cloudflare Clef":0.5955,"cloudflare/clef-flash":0.3299,"cloudflare/clef-omni":0.2298,"liquid/d1-ultra":0.28131884207255187,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.849009187380581,"open/robojev-27b":null,"open/robojev-4b-v2":0.18645454237490924,"open/robojev-4b-v3@0.25":0.7981867790222168,"open/robojev-4b-v3@0.5":0.8290553898010261,"open/robojev-4b-v3@0.75":0.8704295270205443,"open/robojev-4b-v3":0.8874762480971222,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.3376570394916715,"respan/span-02":0.13950785,"typesafe/jev-1.13":0.36,"JEV-27B-VL (10 frames)":0.7466564325011518,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.03564453125}},{"suite":"so101","id":"cable_unclip/molmoact2/eval_cable_unclip_15h58m_08-jul-2026/ep000008","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000008","predictions":{"RoboJev-27B":0.10141659593883964,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.1914590259842172,"TypeSafe Jev 1.14":0.23,"Perplexity Decider":0.07595778875155614,"Liquid D1":0.19193279106941588,"Mercury Decide":0.04208772340991573,"Cloudflare Clef":0.3374,"cloudflare/clef-flash":0.2178,"cloudflare/clef-omni":0.1155,"liquid/d1-ultra":0.093572388802724,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.07519604771475992,"open/robojev-27b":null,"open/robojev-4b-v2":0.04392481517503748,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.011276606158891207,"open/robojev-4b-v3@0.75":0.007532610956861541,"open/robojev-4b-v3":0.006007651396687169,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.21038836231618022,"respan/span-02":0.13179463,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.16389854587565558,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0223388671875}},{"suite":"so101","id":"cable_unclip/molmoact2/eval_debug_task_cell_3_12h06m_27-jun-2026/ep000003","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000003","predictions":{"RoboJev-27B":0.07239016023094433,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.023473564933136338,"TypeSafe Jev 1.14":0.15,"Perplexity Decider":0.04132532215696698,"Liquid D1":0.1008786186753556,"Mercury Decide":0.007577241954192508,"Cloudflare Clef":0.2757,"cloudflare/clef-flash":0.152,"cloudflare/clef-omni":0.109,"liquid/d1-ultra":0.1117174306097684,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.01062774136093478,"open/robojev-27b":null,"open/robojev-4b-v2":0.07585818098994364,"open/robojev-4b-v3@0.25":0.03308597952127457,"open/robojev-4b-v3@0.5":0.01560037702180545,"open/robojev-4b-v3@0.75":0.016188346495106164,"open/robojev-4b-v3":0.01958823717659324,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.11197009410327989,"respan/span-02":0.05358624,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.11896045611500453,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0091552734375}},{"suite":"so101","id":"cable_unclip/molmoact2/eval_debug_task_cell_3_12h06m_27-jun-2026/ep000007","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000007","predictions":{"RoboJev-27B":0.8650176065750195,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.92,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.6835185788186595,"TypeSafe Jev 1.14":0.21,"Perplexity Decider":0.4091470181428776,"Liquid D1":0.4073334000459302,"Mercury Decide":0.7057850154599563,"Cloudflare Clef":0.5028,"cloudflare/clef-flash":0.2653,"cloudflare/clef-omni":0.2237,"liquid/d1-ultra":0.2617952399152932,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.6619115781447364,"open/robojev-27b":null,"open/robojev-4b-v2":0.03251944279343901,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.4345875784292984,"open/robojev-4b-v3@0.75":0.5883486159258515,"open/robojev-4b-v3":0.31845749647192534,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.26718310129432515,"respan/span-02":0.17799917,"typesafe/jev-1.13":0.18,"JEV-27B-VL (10 frames)":0.6231372535682471,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.044677734375}},{"suite":"so101","id":"cable_unclip/molmoact2/eval_debug_task_cell_3_12h06m_27-jun-2026/ep000010","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000010","predictions":{"RoboJev-27B":0.1167165886836965,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":0.07724640879930741,"TypeSafe Jev 1.14":0.19,"Perplexity Decider":0.04684133812487187,"Liquid D1":0.679178699175393,"Mercury Decide":0.01406362952265135,"Cloudflare Clef":0.3383,"cloudflare/clef-flash":0.2422,"cloudflare/clef-omni":0.1683,"liquid/d1-ultra":0.16396262737790857,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.03796977741348605,"open/robojev-27b":null,"open/robojev-4b-v2":0.10087862681469857,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.1804712758005596,"open/robojev-4b-v3@0.75":0.7333927218765676,"open/robojev-4b-v3":0.7267629994168858,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.10296900811945213,"respan/span-02":0.12851425,"typesafe/jev-1.13":0.24,"JEV-27B-VL (10 frames)":0.728699140146225,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00592041015625}},{"suite":"so101","id":"cable_unclip/pi0.5/eval_debug_task_cell_3_08h29m_30-jun-2026/ep000002","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000002","predictions":{"RoboJev-27B":0.9790341386991608,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.8918888492928393,"TypeSafe Jev 1.14":0.77,"Perplexity Decider":0.9359953551574421,"Liquid D1":0.9241418252018903,"Mercury Decide":0.9953904273548458,"Cloudflare Clef":0.5559,"cloudflare/clef-flash":0.2743,"cloudflare/clef-omni":0.1917,"liquid/d1-ultra":0.8613434779003615,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.9831153423301643,"open/robojev-27b":null,"open/robojev-4b-v2":0.9106362662233711,"open/robojev-4b-v3@0.25":0.8933094143867493,"open/robojev-4b-v3@0.5":0.9143873376244105,"open/robojev-4b-v3@0.75":0.9198621986336036,"open/robojev-4b-v3":0.828649621504827,"openai/gpt-6-luna-decisions":0.88,"perplexity/pplx-decider-flash-v1.2":0.5600324876688471,"respan/span-02":0.14244798,"typesafe/jev-1.13":0.6,"JEV-27B-VL (10 frames)":0.7478128320685609,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2490234375}},{"suite":"so101","id":"cable_unclip/pi0.5/eval_debug_task_cell_3_08h29m_30-jun-2026/ep000005","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000005","predictions":{"RoboJev-27B":0.031861159124929025,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.011607404058322229,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.021000140068757615,"Liquid D1":0.06008665354025422,"Mercury Decide":0.004609572281931243,"Cloudflare Clef":0.3417,"cloudflare/clef-flash":0.2014,"cloudflare/clef-omni":0.1778,"liquid/d1-ultra":0.2617952490134856,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.005257839017731877,"open/robojev-27b":null,"open/robojev-4b-v2":0.009538288429694562,"open/robojev-4b-v3@0.25":0.03308597952127457,"open/robojev-4b-v3@0.5":0.010566189227213266,"open/robojev-4b-v3@0.75":0.011381877728436919,"open/robojev-4b-v3":0.008304581719395627,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.1087898432085028,"respan/span-02":0.04159407,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.3386558974671885,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0216064453125}},{"suite":"so101","id":"cable_unclip/pi0.5/eval_debug_task_cell_3_08h29m_30-jun-2026/ep000009","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000009","predictions":{"RoboJev-27B":0.05352851297826965,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.009234748807882645,"TypeSafe Jev 1.14":0.2,"Perplexity Decider":0.03287994593311355,"Liquid D1":0.2689414096510108,"Mercury Decide":0.0040701374554085205,"Cloudflare Clef":0.4495,"cloudflare/clef-flash":0.2484,"cloudflare/clef-omni":0.2004,"liquid/d1-ultra":0.17794900662645483,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.003946438109571003,"open/robojev-27b":null,"open/robojev-4b-v2":0.007644678711335276,"open/robojev-4b-v3@0.25":0.18242551386356354,"open/robojev-4b-v3@0.5":0.10858632498619036,"open/robojev-4b-v3@0.75":0.22270014231977903,"open/robojev-4b-v3":0.14264680034200217,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3383665743410279,"respan/span-02":0.07187633,"typesafe/jev-1.13":0.23,"JEV-27B-VL (10 frames)":0.6307027607068137,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.012451171875}},{"suite":"so101","id":"cable_unclip/pi0.5/eval_debug_task_cell_3_08h29m_30-jun-2026/ep000012","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000012","predictions":{"RoboJev-27B":0.9552812607916535,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.749037207192824,"TypeSafe Jev 1.14":0.68,"Perplexity Decider":0.7068298533032371,"Liquid D1":0.6224593312018546,"Mercury Decide":0.9890130589278814,"Cloudflare Clef":0.6059,"cloudflare/clef-flash":0.2325,"cloudflare/clef-omni":0.148,"liquid/d1-ultra":0.6439101958177847,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.9588826142297452,"open/robojev-27b":null,"open/robojev-4b-v2":0.010890344798324344,"open/robojev-4b-v3@0.25":0.8354835510253906,"open/robojev-4b-v3@0.5":0.9442201868171092,"open/robojev-4b-v3@0.75":0.9456867338168167,"open/robojev-4b-v3":0.881933594679255,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.5334124172773226,"respan/span-02":0.09350972,"typesafe/jev-1.13":0.34,"JEV-27B-VL (10 frames)":0.7619944895839154,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.12353515625}},{"suite":"so101","id":"cable_unclip/pi0.5/eval_debug_task_cell_3_08h38m_30-jun-2026/ep000001","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000001","predictions":{"RoboJev-27B":0.9631724163297589,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.8611886888225119,"TypeSafe Jev 1.14":0.72,"Perplexity Decider":0.8583883415043733,"Liquid D1":0.9149009561531425,"Mercury Decide":0.9740426398352605,"Cloudflare Clef":0.6785,"cloudflare/clef-flash":0.3159,"cloudflare/clef-omni":0.2785,"liquid/d1-ultra":0.6982966523528483,"open/intern-decision-4b":0.36247442200877295,"open/robojev-27b-v1@0.5":0.9843737187871909,"open/robojev-27b":null,"open/robojev-4b-v2":0.03251944279343901,"open/robojev-4b-v3@0.25":0.9046505093574524,"open/robojev-4b-v3@0.5":0.9193991005705059,"open/robojev-4b-v3@0.75":0.93575028740662,"open/robojev-4b-v3":0.9118918620554844,"openai/gpt-6-luna-decisions":0.86,"perplexity/pplx-decider-flash-v1.2":0.5567803990313253,"respan/span-02":0.16402,"typesafe/jev-1.13":0.66,"JEV-27B-VL (10 frames)":0.829041530489087,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.27734375}},{"suite":"so101","id":"cable_unclip/pi0.5/eval_debug_task_cell_3_08h38m_30-jun-2026/ep000003","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000003","predictions":{"RoboJev-27B":0.08196750996511741,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.025881673130120526,"TypeSafe Jev 1.14":0.13,"Perplexity Decider":0.07238384641105111,"Liquid D1":0.30735801686526387,"Mercury Decide":0.007577241547996189,"Cloudflare Clef":0.293,"cloudflare/clef-flash":0.2191,"cloudflare/clef-omni":0.205,"liquid/d1-ultra":0.09357237882026916,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.025222407391463534,"open/robojev-27b":null,"open/robojev-4b-v2":0.012431651137415392,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.020201721614979237,"open/robojev-4b-v3@0.75":0.0171641516746209,"open/robojev-4b-v3":0.020659669708358676,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.3766251407461873,"respan/span-02":0.045718655,"typesafe/jev-1.13":0.19,"JEV-27B-VL (10 frames)":0.28358029478140306,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0091552734375}},{"suite":"so101","id":"cable_unclip/pi0.5/eval_debug_task_cell_3_08h38m_30-jun-2026/ep000004","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000004","predictions":{"RoboJev-27B":0.03806149143058357,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.04553687902278685,"TypeSafe Jev 1.14":0.11,"Perplexity Decider":0.03260985062184276,"Liquid D1":0.17328820592932656,"Mercury Decide":0.01798620677085449,"Cloudflare Clef":0.3407,"cloudflare/clef-flash":0.1756,"cloudflare/clef-omni":0.1553,"liquid/d1-ultra":0.17084219680252014,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.02130399226614878,"open/robojev-27b":null,"open/robojev-4b-v2":0.007990902069952163,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.013703364243695216,"open/robojev-4b-v3@0.75":0.013576917981093352,"open/robojev-4b-v3":0.010300413398065098,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.08581908834068283,"respan/span-02":0.06876188,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.2260135385939016,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01495361328125}},{"suite":"so101","id":"cable_unclip/pi0.5/eval_debug_task_cell_3_08h38m_30-jun-2026/ep000005","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000005","predictions":{"RoboJev-27B":0.6258676730516575,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.20617617277538214,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.13698677178401325,"Liquid D1":0.24508500210441886,"Mercury Decide":0.029312231705318298,"Cloudflare Clef":0.4108,"cloudflare/clef-flash":0.2366,"cloudflare/clef-omni":0.1825,"liquid/d1-ultra":0.2254616160560029,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.1915113013248747,"open/robojev-27b":null,"open/robojev-4b-v2":0.012431651137415392,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.020201721614979237,"open/robojev-4b-v3@0.75":0.02297736967873775,"open/robojev-4b-v3":0.021788411170123766,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.13877345637489963,"respan/span-02":0.04833265,"typesafe/jev-1.13":0.21,"JEV-27B-VL (10 frames)":0.31156638564452294,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00421142578125}},{"suite":"so101","id":"cable_unclip/pi0.5/eval_debug_task_cell_3_08h38m_30-jun-2026/ep000009","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000009","predictions":{"RoboJev-27B":0.6704961992204733,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.07,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.35,"JEV-27B-VL":0.35764336731027874,"TypeSafe Jev 1.14":0.36,"Perplexity Decider":0.13445373618094789,"Liquid D1":0.2942149845400438,"Mercury Decide":0.11920292828022305,"Cloudflare Clef":0.3657,"cloudflare/clef-flash":0.2335,"cloudflare/clef-omni":0.1287,"liquid/d1-ultra":0.2431681574404313,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.2923837429930969,"open/robojev-27b":null,"open/robojev-4b-v2":0.01549249627965257,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.0671334948723516,"open/robojev-4b-v3@0.75":0.13643297762397494,"open/robojev-4b-v3":0.21343419258585974,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.12247098268606497,"respan/span-02":0.05091989,"typesafe/jev-1.13":0.22,"JEV-27B-VL (10 frames)":0.5404283298490254,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006683349609375}},{"suite":"so101","id":"cable_unclip/pi0/eval_debug_task_cell_3_07h53m_30-jun-2026/ep000001","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000001","predictions":{"RoboJev-27B":0.049336992736365506,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.09541036674294419,"TypeSafe Jev 1.14":0.17,"Perplexity Decider":0.05518113545238502,"Liquid D1":0.37754066879814546,"Mercury Decide":0.03308597898458846,"Cloudflare Clef":0.4193,"cloudflare/clef-flash":0.2529,"cloudflare/clef-omni":0.1494,"liquid/d1-ultra":0.18528535894060336,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.025717109167908935,"open/robojev-27b":null,"open/robojev-4b-v2":0.012431651137415392,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.02612421708095358,"open/robojev-4b-v3@0.75":0.018197691623827453,"open/robojev-4b-v3":0.01421514020851167,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.10699086517282466,"respan/span-02":0.08173537,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.21280402855310412,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.012451171875}},{"suite":"so101","id":"cable_unclip/pi0/eval_debug_task_cell_3_07h53m_30-jun-2026/ep000004","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000004","predictions":{"RoboJev-27B":0.9527518826983283,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.7174274895779578,"TypeSafe Jev 1.14":0.71,"Perplexity Decider":0.3676557578953101,"Liquid D1":0.817574471748733,"Mercury Decide":0.9579122756889438,"Cloudflare Clef":0.7058,"cloudflare/clef-flash":0.2379,"cloudflare/clef-omni":0.1356,"liquid/d1-ultra":0.1708422101401565,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.8455593353315417,"open/robojev-27b":null,"open/robojev-4b-v2":0.03863165331656982,"open/robojev-4b-v3@0.25":0.8807970285415649,"open/robojev-4b-v3@0.5":0.9193991005705059,"open/robojev-4b-v3@0.75":0.9282107321543306,"open/robojev-4b-v3":0.863871653255755,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.4221130642159177,"respan/span-02":0.06390847,"typesafe/jev-1.13":0.35,"JEV-27B-VL (10 frames)":0.838928693536204,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1630859375}},{"suite":"so101","id":"cable_unclip/pi0/eval_debug_task_cell_3_07h53m_30-jun-2026/ep000007","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000007","predictions":{"RoboJev-27B":0.9664760204730266,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.65,"JEV-27B-VL":0.8639279663062321,"TypeSafe Jev 1.14":0.43,"Perplexity Decider":0.8732198418787173,"Liquid D1":0.8519527944504226,"Mercury Decide":0.9933071504068844,"Cloudflare Clef":0.7055,"cloudflare/clef-flash":0.2858,"cloudflare/clef-omni":0.1487,"liquid/d1-ultra":0.7830419080912434,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.9903819469140583,"open/robojev-27b":null,"open/robojev-4b-v2":0.028559627850600573,"open/robojev-4b-v3@0.25":0.8933094143867493,"open/robojev-4b-v3@0.5":0.9368711827232762,"open/robojev-4b-v3@0.75":0.9566958954509301,"open/robojev-4b-v3":0.9118918620554844,"openai/gpt-6-luna-decisions":0.44,"perplexity/pplx-decider-flash-v1.2":0.15228556086211806,"respan/span-02":0.06334337,"typesafe/jev-1.13":0.44,"JEV-27B-VL (10 frames)":0.8006758620033994,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.494140625}},{"suite":"so101","id":"cable_unclip/pi0/eval_debug_task_cell_3_08h03m_30-jun-2026/ep000002","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000002","predictions":{"RoboJev-27B":0.11820022909577964,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.08,"JEV-27B-VL":0.07835160049350365,"TypeSafe Jev 1.14":0.18,"Perplexity Decider":0.07209516938786886,"Liquid D1":0.3629692055196168,"Mercury Decide":0.012431650464431697,"Cloudflare Clef":0.2863,"cloudflare/clef-flash":0.2323,"cloudflare/clef-omni":0.161,"liquid/d1-ultra":0.24316815744043135,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.01850806305155569,"open/robojev-27b":null,"open/robojev-4b-v2":0.02297736939860946,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.029688941289226882,"open/robojev-4b-v3@0.75":0.032519444419615386,"open/robojev-4b-v3":0.04100570699541391,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.15578304423790024,"respan/span-02":0.08201439,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.5774291534157067,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.12158203125}},{"suite":"so101","id":"cable_unclip/pi0/eval_debug_task_cell_3_08h03m_30-jun-2026/ep000004","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000004","predictions":{"RoboJev-27B":0.11583782205267935,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.06,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.034636063359499696,"TypeSafe Jev 1.14":0.16,"Perplexity Decider":0.028347074110365394,"Liquid D1":0.19193278644723683,"Mercury Decide":0.0109869404851608,"Cloudflare Clef":0.2254,"cloudflare/clef-flash":0.1833,"cloudflare/clef-omni":0.13,"liquid/d1-ultra":0.1386565052319944,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.005877674176117899,"open/robojev-27b":null,"open/robojev-4b-v2":0.018465477873242233,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.022977370307335907,"open/robojev-4b-v3@0.75":0.02167836395087896,"open/robojev-4b-v3":0.021788411170123766,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.09260648693749736,"respan/span-02":0.05628982,"typesafe/jev-1.13":0.09,"JEV-27B-VL (10 frames)":0.29286659488950534,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.03466796875}},{"suite":"so101","id":"cable_unclip/pi0/eval_debug_task_cell_3_08h15m_30-jun-2026/ep000001","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000001","predictions":{"RoboJev-27B":0.5085269421941676,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.07,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.3791446580869453,"TypeSafe Jev 1.14":0.4,"Perplexity Decider":0.23841024919149229,"Liquid D1":0.6224593452091672,"Mercury Decide":0.1329642281726931,"Cloudflare Clef":0.4219,"cloudflare/clef-flash":0.2019,"cloudflare/clef-omni":0.118,"liquid/d1-ultra":0.47533768343489957,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.5045756463362492,"open/robojev-27b":null,"open/robojev-4b-v2":0.02618406111961536,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.45081746874907896,"open/robojev-4b-v3@0.75":0.756014627783845,"open/robojev-4b-v3":0.7677504278026662,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.40037129939493493,"respan/span-02":0.04012936,"typesafe/jev-1.13":0.26,"JEV-27B-VL (10 frames)":0.4649861801936181,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0145263671875}},{"suite":"so101","id":"cable_unclip/smolvla/eval_debug_task_cell_3_10h33m_24-jun-2026/ep000005","task":"Remove the power cable from cable holder","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000005","predictions":{"RoboJev-27B":0.5115057048138648,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.1938550270197048,"TypeSafe Jev 1.14":0.33,"Perplexity Decider":0.042768205060866246,"Liquid D1":0.5621765008857981,"Mercury Decide":0.04208772656390786,"Cloudflare Clef":0.3938,"cloudflare/clef-flash":0.2796,"cloudflare/clef-omni":0.165,"liquid/d1-ultra":0.2714469192385764,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.0738174238094843,"open/robojev-27b":null,"open/robojev-4b-v2":0.02618406111961536,"open/robojev-4b-v3@0.25":0.22270014882087708,"open/robojev-4b-v3@0.5":0.08060089942949411,"open/robojev-4b-v3@0.75":0.06424971259337996,"open/robojev-4b-v3":0.05593065484668503,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.3049650820416235,"respan/span-02":0.299406,"typesafe/jev-1.13":0.31,"JEV-27B-VL (10 frames)":0.5532303198359114,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0966796875}},{"suite":"so101","id":"cable_unclip/smolvla/eval_debug_task_cell_3_10h33m_24-jun-2026/ep000017","task":"Remove the power cable from cable holder","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"cable_unclip","episode":"ep000017","predictions":{"RoboJev-27B":0.052300360422123666,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.03412466860712587,"TypeSafe Jev 1.14":0.13,"Perplexity Decider":0.05831069256464793,"Liquid D1":0.4073334000459302,"Mercury Decide":0.01243165304850344,"Cloudflare Clef":0.2808,"cloudflare/clef-flash":0.2363,"cloudflare/clef-omni":0.1396,"liquid/d1-ultra":0.13865650242072058,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":0.04537039020528788,"open/robojev-27b":null,"open/robojev-4b-v2":0.033953688356658976,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.07137286741841814,"open/robojev-4b-v3@0.75":0.15107550847556014,"open/robojev-4b-v3":0.45932920505823327,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.2270633643600022,"respan/span-02":0.09910127,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.17017731373057982,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.003173828125}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000000","task":"Put the eye drops into the basket","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000000","predictions":{"RoboJev-27B":0.9944686837651066,"GPT-6 Astra":0.9,"GPT-6.1 Sol":0.91,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.32815409860942907,"TypeSafe Jev 1.14":0.31,"Perplexity Decider":0.7523598413766159,"Liquid D1":0.1732881888514755,"Mercury Decide":0.9149009636941993,"Cloudflare Clef":0.3096,"cloudflare/clef-flash":0.1995,"cloudflare/clef-omni":0.072,"liquid/d1-ultra":0.19285322709400265,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.9466660088144017,"open/robojev-27b":null,"open/robojev-4b-v2":0.001842766452331557,"open/robojev-4b-v3@0.25":0.3486451506614685,"open/robojev-4b-v3@0.5":0.9537489247538957,"open/robojev-4b-v3@0.75":0.9655548037210256,"open/robojev-4b-v3":0.952080652301484,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.3399958049494602,"respan/span-02":0.10549836,"typesafe/jev-1.13":0.29,"JEV-27B-VL (10 frames)":0.9495464663334968,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.010009765625}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000001","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000001","predictions":{"RoboJev-27B":0.006719524764722863,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.04454307180629802,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.03632952581658215,"Liquid D1":0.15610489351941398,"Mercury Decide":0.01798621302173174,"Cloudflare Clef":0.237,"cloudflare/clef-flash":0.1597,"cloudflare/clef-omni":0.0608,"liquid/d1-ultra":0.11671092279806906,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.003232265120123761,"open/robojev-27b":null,"open/robojev-4b-v2":0.001842766452331557,"open/robojev-4b-v3@0.25":0.020332353189587593,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.0030982660175204184,"open/robojev-4b-v3":0.0017286305758914561,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1516315024092271,"respan/span-02":0.03816063,"typesafe/jev-1.13":0.19,"JEV-27B-VL (10 frames)":0.006182824109201361,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.010986328125}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000002","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000002","predictions":{"RoboJev-27B":0.00637535964537462,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.13601654707145427,"TypeSafe Jev 1.14":0.14,"Perplexity Decider":0.09639205615588041,"Liquid D1":0.04742587856304458,"Mercury Decide":0.04742587587030561,"Cloudflare Clef":0.2122,"cloudflare/clef-flash":0.1233,"cloudflare/clef-omni":0.0623,"liquid/d1-ultra":0.12728025747683813,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.012029797109730943,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016121527751335812,"open/robojev-4b-v3@0.25":0.020332353189587593,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.0029197498822566025,"open/robojev-4b-v3":0.0017286305758914561,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.17997362053855961,"respan/span-02":0.07720277,"typesafe/jev-1.13":0.2,"JEV-27B-VL (10 frames)":0.0659927621976559,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.010009765625}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000003","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000003","predictions":{"RoboJev-27B":0.005946737110254221,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.03337120605512402,"TypeSafe Jev 1.14":0.13,"Perplexity Decider":0.052642776407675826,"Liquid D1":0.0715911984541334,"Mercury Decide":0.008577483394141454,"Cloudflare Clef":0.2149,"cloudflare/clef-flash":0.1329,"cloudflare/clef-omni":0.058,"liquid/d1-ultra":0.17084221014015646,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.0035132880424230237,"open/robojev-27b":null,"open/robojev-4b-v2":0.0015418730931173695,"open/robojev-4b-v3@0.25":0.01798621006309986,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.0037017607703716303,"open/robojev-4b-v3":0.0022671624120110317,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.19394613825313692,"respan/span-02":0.037081476,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.010536865406362925,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01068115234375}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000004","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000004","predictions":{"RoboJev-27B":0.005187863411411752,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.012336023844016162,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.024548480566281422,"Liquid D1":0.14033626027631768,"Mercury Decide":0.003172682821867274,"Cloudflare Clef":0.1784,"cloudflare/clef-flash":0.1972,"cloudflare/clef-omni":0.0583,"liquid/d1-ultra":0.021858139913410856,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.0005112647116330681,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016121527751335812,"open/robojev-4b-v3@0.25":0.022977370768785477,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.00204466165068541,"open/robojev-4b-v3":0.001004586699177363,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.10007198848358054,"respan/span-02":0.048843067,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.01370752920338269,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.008056640625}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000005","task":"Put the eye drops into the basket","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000005","predictions":{"RoboJev-27B":0.9946754466139978,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.91,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.6666265717535418,"TypeSafe Jev 1.14":0.29,"Perplexity Decider":0.7757606241625665,"Liquid D1":0.3923368443773709,"Mercury Decide":0.9669140179168129,"Cloudflare Clef":0.1988,"cloudflare/clef-flash":0.1622,"cloudflare/clef-omni":0.0582,"liquid/d1-ultra":0.6325127074476207,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.9315740264628504,"open/robojev-27b":null,"open/robojev-4b-v2":0.001410358480093293,"open/robojev-4b-v3@0.25":0.9149009585380554,"open/robojev-4b-v3@0.5":0.9640659266906685,"open/robojev-4b-v3@0.75":0.9541617453379198,"open/robojev-4b-v3":0.9380451002706788,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.20627363949179164,"respan/span-02":0.06815856,"typesafe/jev-1.13":0.3,"JEV-27B-VL (10 frames)":0.6564602285644219,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00537109375}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000006","task":"Put the eye drops into the basket","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000006","predictions":{"RoboJev-27B":0.9751588127664976,"GPT-6 Astra":0.92,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.6768165870719258,"TypeSafe Jev 1.14":0.42,"Perplexity Decider":0.754718459675905,"Liquid D1":0.7549149868676283,"Mercury Decide":0.9579122723847614,"Cloudflare Clef":0.436,"cloudflare/clef-flash":0.1923,"cloudflare/clef-omni":0.076,"liquid/d1-ultra":0.3229012912817457,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.9487447232040961,"open/robojev-27b":null,"open/robojev-4b-v2":0.0025170615300917137,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.8780062831580779,"open/robojev-4b-v3@0.75":0.863567022376025,"open/robojev-4b-v3":0.8505765771600906,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.20176790748680543,"respan/span-02":0.06446677,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.5712677535071656,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01324462890625}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000007","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000007","predictions":{"RoboJev-27B":0.011497999245177803,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.07040458501505098,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.07373957470849118,"Liquid D1":0.23370635691404026,"Mercury Decide":0.01798620650765971,"Cloudflare Clef":0.3023,"cloudflare/clef-flash":0.2173,"cloudflare/clef-omni":0.0689,"liquid/d1-ultra":0.18528535538729296,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.0048054480993172,"open/robojev-27b":null,"open/robojev-4b-v2":0.004905405551811006,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.009900079472737449,"open/robojev-4b-v3@0.75":0.005604465074944334,"open/robojev-4b-v3":0.005108442412304043,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.31593318728315184,"respan/span-02":0.08673384,"typesafe/jev-1.13":0.2,"JEV-27B-VL (10 frames)":0.014082453420271307,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00445556640625}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000008","task":"Put the eye drops into the basket","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000008","predictions":{"RoboJev-27B":0.9914141443464679,"GPT-6 Astra":0.93,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.6369217727935144,"TypeSafe Jev 1.14":0.49,"Perplexity Decider":0.5463136598706725,"Liquid D1":0.1561048974454574,"Mercury Decide":0.7310585786300049,"Cloudflare Clef":0.3101,"cloudflare/clef-flash":0.1723,"cloudflare/clef-omni":0.0586,"liquid/d1-ultra":0.6439101958177847,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.8560008825008488,"open/robojev-27b":null,"open/robojev-4b-v2":0.001410358480093293,"open/robojev-4b-v3@0.25":0.7549149990081787,"open/robojev-4b-v3@0.5":0.9662767595980272,"open/robojev-4b-v3@0.75":0.9655548037210256,"open/robojev-4b-v3":0.952080652301484,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2520112012769457,"respan/span-02":0.071527965,"typesafe/jev-1.13":0.25,"JEV-27B-VL (10 frames)":0.5405604686627892,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00860595703125}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000009","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000009","predictions":{"RoboJev-27B":0.010578176782796404,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.06671642505761606,"TypeSafe Jev 1.14":0.11,"Perplexity Decider":0.10457779132127051,"Liquid D1":0.2018132174596823,"Mercury Decide":0.02297737036999376,"Cloudflare Clef":0.2144,"cloudflare/clef-flash":0.1949,"cloudflare/clef-omni":0.0532,"liquid/d1-ultra":0.1639626096311206,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.010311023424163351,"open/robojev-27b":null,"open/robojev-4b-v2":0.0023025598229782147,"open/robojev-4b-v3@0.25":0.022977370768785477,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.0029197498822566025,"open/robojev-4b-v3":0.0020341273969387797,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.18628638699840674,"respan/span-02":0.095211685,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.16434460542904286,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.010986328125}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000010","task":"Put the eye drops into the basket","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000010","predictions":{"RoboJev-27B":0.9961660225120447,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.75,"JEV-27B-VL":0.9025351028589279,"TypeSafe Jev 1.14":0.73,"Perplexity Decider":0.9409209880530353,"Liquid D1":0.9149009596336303,"Mercury Decide":0.9669140195852891,"Cloudflare Clef":0.7949,"cloudflare/clef-flash":0.5737,"cloudflare/clef-omni":0.0888,"liquid/d1-ultra":0.6092789156141315,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.9920583604071961,"open/robojev-27b":null,"open/robojev-4b-v2":0.012431651137415392,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.9871579519028945,"open/robojev-4b-v3@0.75":0.978321636049121,"open/robojev-4b-v3":0.9649471836741528,"openai/gpt-6-luna-decisions":0.92,"perplexity/pplx-decider-flash-v1.2":0.8740005890570495,"respan/span-02":0.05894752,"typesafe/jev-1.13":0.73,"JEV-27B-VL (10 frames)":0.9202696644310456,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.8046875}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000011","task":"Put the eye drops into the basket","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000011","predictions":{"RoboJev-27B":0.9946765257741373,"GPT-6 Astra":0.9,"GPT-6.1 Sol":0.92,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.6061339568260653,"TypeSafe Jev 1.14":0.57,"Perplexity Decider":0.8070586750357932,"Liquid D1":0.06008664512463808,"Mercury Decide":0.9399133502467731,"Cloudflare Clef":0.3083,"cloudflare/clef-flash":0.155,"cloudflare/clef-omni":0.0472,"liquid/d1-ultra":0.19285323442217972,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.9446929090212585,"open/robojev-27b":null,"open/robojev-4b-v2":0.0014746525778226533,"open/robojev-4b-v3@0.25":0.9046505093574524,"open/robojev-4b-v3@0.5":0.9507586388020023,"open/robojev-4b-v3@0.75":0.948664203960477,"open/robojev-4b-v3":0.9314191245597471,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.19928714849217238,"respan/span-02":0.050328992,"typesafe/jev-1.13":0.24,"JEV-27B-VL (10 frames)":0.8710645318029012,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0174560546875}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000012","task":"Put the eye drops into the basket","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000012","predictions":{"RoboJev-27B":0.9805583425822942,"GPT-6 Astra":0.93,"GPT-6.1 Sol":0.92,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.20117936953915216,"TypeSafe Jev 1.14":0.37,"Perplexity Decider":0.20889534994914213,"Liquid D1":0.8519527869325346,"Mercury Decide":0.03308597958047282,"Cloudflare Clef":0.4684,"cloudflare/clef-flash":0.26,"cloudflare/clef-omni":0.0617,"liquid/d1-ultra":0.7568318512236519,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.09708649443685864,"open/robojev-27b":null,"open/robojev-4b-v2":0.003593602817215226,"open/robojev-4b-v3@0.25":0.29421496391296387,"open/robojev-4b-v3@0.5":0.8631975135960346,"open/robojev-4b-v3@0.75":0.8832743426844196,"open/robojev-4b-v3":0.870137379491907,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2526529784117865,"respan/span-02":0.05528684,"typesafe/jev-1.13":0.38,"JEV-27B-VL (10 frames)":0.7531360056851455,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00830078125}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000013","task":"Put the eye drops into the basket","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000013","predictions":{"RoboJev-27B":0.9800153005628522,"GPT-6 Astra":0.87,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.38825123165590963,"TypeSafe Jev 1.14":0.4,"Perplexity Decider":0.6096033752579908,"Liquid D1":0.5312093733737563,"Mercury Decide":0.6224593312018546,"Cloudflare Clef":0.3529,"cloudflare/clef-flash":0.1665,"cloudflare/clef-omni":0.0541,"liquid/d1-ultra":0.3560898041822152,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.5374203264682251,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016856305131264125,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.9442201868171092,"open/robojev-4b-v3@0.75":0.9514868285783926,"open/robojev-4b-v3":0.9380451002706788,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.19813552883700955,"respan/span-02":0.04006175,"typesafe/jev-1.13":0.29,"JEV-27B-VL (10 frames)":0.458067344646977,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0206298828125}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000014","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000014","predictions":{"RoboJev-27B":0.00584803349168716,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.014747629634173077,"TypeSafe Jev 1.14":0.07,"Perplexity Decider":0.02766845473242457,"Liquid D1":0.031143831883656593,"Mercury Decide":0.005220125292150274,"Cloudflare Clef":0.2354,"cloudflare/clef-flash":0.1537,"cloudflare/clef-omni":0.05,"liquid/d1-ultra":0.062090641597065205,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.0030110980310758466,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016121527751335812,"open/robojev-4b-v3@0.25":0.014063626527786255,"open/robojev-4b-v3@0.5":0.005872534859081002,"open/robojev-4b-v3@0.75":0.00442228498579546,"open/robojev-4b-v3":0.003897642342744068,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.10245795006178336,"respan/span-02":0.05093593,"typesafe/jev-1.13":0.13,"JEV-27B-VL (10 frames)":0.008717704541828297,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01544189453125}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000015","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000015","predictions":{"RoboJev-27B":0.005142550239739881,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.00441302748223823,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.016039709959637563,"Liquid D1":0.02033235096813516,"Mercury Decide":0.0010987310606588579,"Cloudflare Clef":0.0657,"cloudflare/clef-flash":0.1733,"cloudflare/clef-omni":0.0475,"liquid/d1-ultra":0.022938865044850338,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.0014996809480708232,"open/robojev-27b":null,"open/robojev-4b-v2":0.0014746525778226533,"open/robojev-4b-v3@0.25":0.014063626527786255,"open/robojev-4b-v3@0.5":0.005872534859081002,"open/robojev-4b-v3@0.75":0.0037017607703716303,"open/robojev-4b-v3":0.0022671624120110317,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.08704660374247426,"respan/span-02":0.06668983,"typesafe/jev-1.13":0.15,"JEV-27B-VL (10 frames)":0.0020416081206003096,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0033721923828125}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000016","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000016","predictions":{"RoboJev-27B":0.005991080433110237,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.030062516929684608,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.05201480114743448,"Liquid D1":0.06371498714048861,"Mercury Decide":0.017986213745517662,"Cloudflare Clef":0.0778,"cloudflare/clef-flash":0.1651,"cloudflare/clef-omni":0.065,"liquid/d1-ultra":0.046920384367513654,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.0005498544342800605,"open/robojev-27b":null,"open/robojev-4b-v2":0.0015418730931173695,"open/robojev-4b-v3@0.25":0.01243165135383606,"open/robojev-4b-v3@0.5":0.0032570072049156237,"open/robojev-4b-v3@0.75":0.0017108587429636138,"open/robojev-4b-v3":0.0013913520410630778,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.10988525463760834,"respan/span-02":0.042803396,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.17166364174115908,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.007110595703125}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000017","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000017","predictions":{"RoboJev-27B":0.0044378039251997264,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.10513171601080307,"TypeSafe Jev 1.14":0.22,"Perplexity Decider":0.15202677059687522,"Liquid D1":0.0351448448849122,"Mercury Decide":0.13296425222296632,"Cloudflare Clef":0.2392,"cloudflare/clef-flash":0.1383,"cloudflare/clef-omni":0.0821,"liquid/d1-ultra":0.04476157286064777,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.0063554571632882546,"open/robojev-27b":null,"open/robojev-4b-v2":0.001410358480093293,"open/robojev-4b-v3@0.25":0.014063626527786255,"open/robojev-4b-v3@0.5":0.0037133326112963453,"open/robojev-4b-v3@0.75":0.0027514904934948965,"open/robojev-4b-v3":0.0017286305758914561,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2125708869227856,"respan/span-02":0.07418013,"typesafe/jev-1.13":0.18,"JEV-27B-VL (10 frames)":0.008124131496394486,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00537109375}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000018","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000018","predictions":{"RoboJev-27B":0.004571688940261638,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.03515484459178248,"TypeSafe Jev 1.14":0.11,"Perplexity Decider":0.03306507066147224,"Liquid D1":0.035144842863737535,"Mercury Decide":0.01590639200338161,"Cloudflare Clef":0.1109,"cloudflare/clef-flash":0.188,"cloudflare/clef-omni":0.0619,"liquid/d1-ultra":0.040724814076664326,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.0016538758105032686,"open/robojev-27b":null,"open/robojev-4b-v2":0.001348863876427256,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.0032570072049156237,"open/robojev-4b-v3@0.75":0.0025929030441612317,"open/robojev-4b-v3":0.0015508634943190564,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1657268386873844,"respan/span-02":0.06478788,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.0053631190494938625,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00592041015625}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000019","task":"Put the eye drops into the basket","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000019","predictions":{"RoboJev-27B":0.9815527129348468,"GPT-6 Astra":0.86,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.2999609228852803,"TypeSafe Jev 1.14":0.5,"Perplexity Decider":0.5903049750209887,"Liquid D1":0.5312093733737563,"Mercury Decide":0.9669140237564795,"Cloudflare Clef":0.2713,"cloudflare/clef-flash":0.1873,"cloudflare/clef-omni":0.0798,"liquid/d1-ultra":0.3017033476471517,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.8668720811855055,"open/robojev-27b":null,"open/robojev-4b-v2":0.001842766452331557,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.8195287241994405,"open/robojev-4b-v3@0.75":0.9056724840427216,"open/robojev-4b-v3":0.881933594679255,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2457826488542175,"respan/span-02":0.07493065,"typesafe/jev-1.13":0.29,"JEV-27B-VL (10 frames)":0.8319901631393843,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.044677734375}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000020","task":"Put the eye drops into the basket","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000020","predictions":{"RoboJev-27B":0.9802386625754411,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.22,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.24655649781475023,"TypeSafe Jev 1.14":0.46,"Perplexity Decider":0.19454304071868916,"Liquid D1":0.3073580422436188,"Mercury Decide":0.20181323186177208,"Cloudflare Clef":0.3336,"cloudflare/clef-flash":0.1576,"cloudflare/clef-omni":0.0685,"liquid/d1-ultra":0.19285323442217975,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.21706559801451858,"open/robojev-27b":null,"open/robojev-4b-v2":0.001410358480093293,"open/robojev-4b-v3@0.25":0.07585817575454712,"open/robojev-4b-v3@0.5":0.34121268247291503,"open/robojev-4b-v3@0.75":0.8245695962243903,"open/robojev-4b-v3":0.8126605503046089,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2609060749323819,"respan/span-02":0.11026103,"typesafe/jev-1.13":0.2,"JEV-27B-VL (10 frames)":0.31631563475202085,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01495361328125}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000021","task":"Put the eye drops into the basket","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000021","predictions":{"RoboJev-27B":0.9937121035056977,"GPT-6 Astra":0.9,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.8257238510383728,"TypeSafe Jev 1.14":0.56,"Perplexity Decider":0.8981831518606721,"Liquid D1":0.665410558746814,"Mercury Decide":0.9959298625672426,"Cloudflare Clef":0.3867,"cloudflare/clef-flash":0.1694,"cloudflare/clef-omni":0.0789,"liquid/d1-ultra":0.2813188230362935,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.9683578050231836,"open/robojev-27b":null,"open/robojev-4b-v2":0.0011285254845784295,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.4345875784292984,"open/robojev-4b-v3@0.75":0.8769960242027004,"open/robojev-4b-v3":0.870137379491907,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3628223579673021,"respan/span-02":0.051222246,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.6948800840517203,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0057373046875}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000022","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000022","predictions":{"RoboJev-27B":0.03690619707990269,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.08117815746123622,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.04644749104103969,"Liquid D1":0.32082130082460697,"Mercury Decide":0.047425871831197425,"Cloudflare Clef":0.222,"cloudflare/clef-flash":0.2157,"cloudflare/clef-omni":0.0546,"liquid/d1-ultra":0.30170335260629455,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.009695379674094666,"open/robojev-27b":null,"open/robojev-4b-v2":0.005361080321059209,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.004825770646864498,"open/robojev-4b-v3@0.75":0.0029197498822566025,"open/robojev-4b-v3":0.0022671624120110317,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.08811354077290841,"respan/span-02":0.09834014,"typesafe/jev-1.13":0.24,"JEV-27B-VL (10 frames)":0.14843637960605438,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00592041015625}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000023","task":"Put the eye drops into the basket","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000023","predictions":{"RoboJev-27B":0.9813117505635066,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.91,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.28876293806997827,"TypeSafe Jev 1.14":0.4,"Perplexity Decider":0.34864914191788443,"Liquid D1":0.28140560742914383,"Mercury Decide":0.10669059252545564,"Cloudflare Clef":0.3416,"cloudflare/clef-flash":0.1956,"cloudflare/clef-omni":0.0574,"liquid/d1-ultra":0.46304399869958657,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.2905645456041932,"open/robojev-27b":null,"open/robojev-4b-v2":0.0031445701339940513,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.8848796562508825,"open/robojev-4b-v3@0.75":0.9392374795976737,"open/robojev-4b-v3":0.9411294126132068,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.24149340753170515,"respan/span-02":0.10822503,"typesafe/jev-1.13":0.31,"JEV-27B-VL (10 frames)":0.732613172074541,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006103515625}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000024","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000024","predictions":{"RoboJev-27B":0.005548083560795823,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.18210127651365432,"TypeSafe Jev 1.14":0.18,"Perplexity Decider":0.11528127828154848,"Liquid D1":0.23370635691404026,"Mercury Decide":0.37754066879814546,"Cloudflare Clef":0.3937,"cloudflare/clef-flash":0.1978,"cloudflare/clef-omni":0.0658,"liquid/d1-ultra":0.11171743995346255,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.04892766131784306,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016121527751335812,"open/robojev-4b-v3@0.25":0.07585817575454712,"open/robojev-4b-v3@0.5":0.009275566578748366,"open/robojev-4b-v3@0.75":0.006692850722353873,"open/robojev-4b-v3":0.0048395274167548985,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.25748637743550706,"respan/span-02":0.06600232,"typesafe/jev-1.13":0.31,"JEV-27B-VL (10 frames)":0.004910047650782742,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006500244140625}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000025","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000025","predictions":{"RoboJev-27B":0.004668944412800349,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.08650103753363333,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.10585062939417504,"Liquid D1":0.11279539733570562,"Mercury Decide":0.020332351042339016,"Cloudflare Clef":0.2482,"cloudflare/clef-flash":0.1561,"cloudflare/clef-omni":0.0611,"liquid/d1-ultra":0.07129506702841829,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.003961876112458155,"open/robojev-27b":null,"open/robojev-4b-v2":0.0014746525778226533,"open/robojev-4b-v3@0.25":0.02595735713839531,"open/robojev-4b-v3@0.5":0.004825770646864498,"open/robojev-4b-v3@0.75":0.0029197498822566025,"open/robojev-4b-v3":0.0021474930738670127,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.19111602685189621,"respan/span-02":0.06325504,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.008068418514534301,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.004608154296875}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000026","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000026","predictions":{"RoboJev-27B":0.0062452925483751955,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.014144581093477406,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.04008356032811898,"Liquid D1":0.04742587721667508,"Mercury Decide":0.002182716431146548,"Cloudflare Clef":0.1684,"cloudflare/clef-flash":0.1518,"cloudflare/clef-omni":0.0507,"liquid/d1-ultra":0.06809489773659459,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.002500350709738625,"open/robojev-27b":null,"open/robojev-4b-v2":0.001926734644431273,"open/robojev-4b-v3@0.25":0.009708477184176445,"open/robojev-4b-v3@0.5":0.002675199388665972,"open/robojev-4b-v3@0.75":0.0017108587429636138,"open/robojev-4b-v3":0.0011822765498233803,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.11735680749316252,"respan/span-02":0.07679799,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.0950862300600613,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0021209716796875}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000027","task":"Put the eye drops into the basket","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000027","predictions":{"RoboJev-27B":0.99479394328892,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.691789911339813,"TypeSafe Jev 1.14":0.44,"Perplexity Decider":0.8330853672265928,"Liquid D1":0.18242551491653522,"Mercury Decide":0.9740426456749567,"Cloudflare Clef":0.3405,"cloudflare/clef-flash":0.211,"cloudflare/clef-omni":0.0512,"liquid/d1-ultra":0.4876613324012321,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.9113384971887779,"open/robojev-27b":null,"open/robojev-4b-v2":0.001842766452331557,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.9090947575586418,"open/robojev-4b-v3@0.75":0.9541617453379198,"open/robojev-4b-v3":0.9411294126132068,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.28505446449767124,"respan/span-02":0.05441345,"typesafe/jev-1.13":0.27,"JEV-27B-VL (10 frames)":0.8577475276845834,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0194091796875}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000028","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000028","predictions":{"RoboJev-27B":0.0041064033060925235,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.06695661041490814,"TypeSafe Jev 1.14":0.11,"Perplexity Decider":0.0869812587800024,"Liquid D1":0.02931222841944938,"Mercury Decide":0.025957356114627413,"Cloudflare Clef":0.2819,"cloudflare/clef-flash":0.1401,"cloudflare/clef-omni":0.053,"liquid/d1-ultra":0.07463357580171225,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.004802156530756122,"open/robojev-27b":null,"open/robojev-4b-v2":0.001233791749980779,"open/robojev-4b-v3@0.25":0.01798621006309986,"open/robojev-4b-v3@0.5":0.0037133326112963453,"open/robojev-4b-v3@0.75":0.0023025600819802016,"open/robojev-4b-v3":0.0016373401530355304,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.21305528825721934,"respan/span-02":0.041403033,"typesafe/jev-1.13":0.12,"JEV-27B-VL (10 frames)":0.004948793844198565,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.007110595703125}},{"suite":"so101","id":"eye_drops_to_basket/diffusion/eval_debug_task_cell_3_14h59m_25-jun-2026/ep000029","task":"Put the eye drops into the basket","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_basket","episode":"ep000029","predictions":{"RoboJev-27B":0.004868707256592489,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.080036548264402,"TypeSafe Jev 1.14":0.16,"Perplexity Decider":0.09950302236484841,"Liquid D1":0.060086648490884395,"Mercury Decide":0.24508502416032488,"Cloudflare Clef":0.1716,"cloudflare/clef-flash":0.1877,"cloudflare/clef-omni":0.0597,"liquid/d1-ultra":0.06502832340580617,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.006592372904587374,"open/robojev-27b":null,"open/robojev-4b-v2":0.001410358480093293,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.003964844872971652,"open/robojev-4b-v3@0.75":0.00244343308696661,"open/robojev-4b-v3":0.0016373401530355304,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.22588937071357795,"respan/span-02":0.047867443,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.026186325219923604,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00421142578125}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000001","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000001","predictions":{"RoboJev-27B":0.008726986501008394,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.07296713554583568,"TypeSafe Jev 1.14":0.19,"Perplexity Decider":0.21531738743915765,"Liquid D1":0.09534945975773548,"Mercury Decide":0.16451645880021026,"Cloudflare Clef":0.1876,"cloudflare/clef-flash":0.1388,"cloudflare/clef-omni":0.0649,"liquid/d1-ultra":0.2254616160560029,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":0.005944391146304431,"open/robojev-27b":null,"open/robojev-4b-v2":0.0022022489536237186,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.004825770646864498,"open/robojev-4b-v3@0.75":0.0015191329853098835,"open/robojev-4b-v3":0.0006869178295131179,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.09791397214612564,"respan/span-02":0.04480103,"typesafe/jev-1.13":0.19,"JEV-27B-VL (10 frames)":0.3932246086502527,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0047607421875}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000002","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000002","predictions":{"RoboJev-27B":0.988966931212692,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8365312260233088,"TypeSafe Jev 1.14":0.71,"Perplexity Decider":0.937269664214847,"Liquid D1":0.9896718452721713,"Mercury Decide":0.9924227582699159,"Cloudflare Clef":0.7748,"cloudflare/clef-flash":0.5936,"cloudflare/clef-omni":0.1205,"liquid/d1-ultra":0.8671346687498757,"open/intern-decision-4b":0.8275619327448428,"open/robojev-27b-v1@0.5":0.9584997695652079,"open/robojev-27b":null,"open/robojev-4b-v2":0.9875683488625845,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.9907244334212516,"open/robojev-4b-v3@0.75":0.9838116535048939,"open/robojev-4b-v3":0.9684435763811455,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.828108251722858,"respan/span-02":0.9495323,"typesafe/jev-1.13":0.73,"JEV-27B-VL (10 frames)":0.7610393910416077,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.482421875}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000005","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000005","predictions":{"RoboJev-27B":0.993759128589878,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.9,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.8246126838791916,"TypeSafe Jev 1.14":0.61,"Perplexity Decider":0.9359025946792648,"Liquid D1":0.9859363755911228,"Mercury Decide":0.9890130550013349,"Cloudflare Clef":0.8212,"cloudflare/clef-flash":0.1751,"cloudflare/clef-omni":0.1003,"liquid/d1-ultra":0.6770986984253415,"open/intern-decision-4b":0.788764540067536,"open/robojev-27b-v1@0.5":0.9694931782166766,"open/robojev-27b":null,"open/robojev-4b-v2":0.9870081646084733,"open/robojev-4b-v3@0.25":0.9840936064720154,"open/robojev-4b-v3@0.5":0.9871579519028945,"open/robojev-4b-v3@0.75":0.9828358483253791,"open/robojev-4b-v3":0.9700628546674281,"openai/gpt-6-luna-decisions":0.9,"perplexity/pplx-decider-flash-v1.2":0.7381879336942836,"respan/span-02":0.34133285,"typesafe/jev-1.13":0.69,"JEV-27B-VL (10 frames)":0.8521322890520037,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2392578125}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000006","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000006","predictions":{"RoboJev-27B":0.9905451912407826,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8234959400245555,"TypeSafe Jev 1.14":0.72,"Perplexity Decider":0.9439380470115678,"Liquid D1":0.9914225126221561,"Mercury Decide":0.9465966728366375,"Cloudflare Clef":0.7652,"cloudflare/clef-flash":0.3208,"cloudflare/clef-omni":0.0906,"liquid/d1-ultra":0.7913111107586915,"open/intern-decision-4b":0.767101934678807,"open/robojev-27b-v1@0.5":0.9183651958108863,"open/robojev-27b":null,"open/robojev-4b-v2":0.9912693183717645,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.9833564251170067,"open/robojev-4b-v3@0.75":0.9756477227346713,"open/robojev-4b-v3":0.9545001271117012,"openai/gpt-6-luna-decisions":0.9,"perplexity/pplx-decider-flash-v1.2":0.855980166199083,"respan/span-02":0.86195326,"typesafe/jev-1.13":0.67,"JEV-27B-VL (10 frames)":0.8823012242680964,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.416015625}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000007","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000007","predictions":{"RoboJev-27B":0.012489296275850928,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.032151010576124545,"TypeSafe Jev 1.14":0.28,"Perplexity Decider":0.32061166591824325,"Liquid D1":0.1561048974454574,"Mercury Decide":0.13296423160844623,"Cloudflare Clef":0.1992,"cloudflare/clef-flash":0.1397,"cloudflare/clef-omni":0.062,"liquid/d1-ultra":0.20868888535414212,"open/intern-decision-4b":0.1395062328236417,"open/robojev-27b-v1@0.5":0.0016176259854203596,"open/robojev-27b":null,"open/robojev-4b-v2":0.0024074285712443492,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.007626874902958847,"open/robojev-4b-v3@0.75":0.0023025600819802016,"open/robojev-4b-v3":0.0009012109819517691,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1702362480382679,"respan/span-02":0.052166972,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.13300517049040664,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.016357421875}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000008","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000008","predictions":{"RoboJev-27B":0.013200770246803212,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.061408392147026036,"TypeSafe Jev 1.14":0.33,"Perplexity Decider":0.2566376345258732,"Liquid D1":0.05665243167886765,"Mercury Decide":0.09534945718704857,"Cloudflare Clef":0.2065,"cloudflare/clef-flash":0.1292,"cloudflare/clef-omni":0.0643,"liquid/d1-ultra":0.2086888775798098,"open/intern-decision-4b":0.13214384255458153,"open/robojev-27b-v1@0.5":0.003702477194044692,"open/robojev-27b":null,"open/robojev-4b-v2":0.0031445701339940513,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.008141294289513608,"open/robojev-4b-v3@0.75":0.0016121526329810115,"open/robojev-4b-v3":0.0006506053076953617,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.16744974494964573,"respan/span-02":0.03150718,"typesafe/jev-1.13":0.25,"JEV-27B-VL (10 frames)":0.21068688789659987,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0091552734375}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000010","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000010","predictions":{"RoboJev-27B":0.007977572287196482,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.12383456021342108,"TypeSafe Jev 1.14":0.27,"Perplexity Decider":0.31793665322717435,"Liquid D1":0.13296424706933604,"Mercury Decide":0.29421496597446145,"Cloudflare Clef":0.2632,"cloudflare/clef-flash":0.1318,"cloudflare/clef-omni":0.0659,"liquid/d1-ultra":0.22546162016657334,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":0.013630734226005184,"open/robojev-27b":null,"open/robojev-4b-v2":0.0031445701339940513,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.004825770646864498,"open/robojev-4b-v3@0.75":0.0013488637996850762,"open/robojev-4b-v3":0.0005235534182684861,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1540611048897434,"respan/span-02":0.051899407,"typesafe/jev-1.13":0.21,"JEV-27B-VL (10 frames)":0.0561145451921629,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.007354736328125}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000011","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000011","predictions":{"RoboJev-27B":0.008911379881015837,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.159236089034446,"TypeSafe Jev 1.14":0.3,"Perplexity Decider":0.47493557729837393,"Liquid D1":0.256831980010821,"Mercury Decide":0.7057850402140659,"Cloudflare Clef":0.1717,"cloudflare/clef-flash":0.1005,"cloudflare/clef-omni":0.0647,"liquid/d1-ultra":0.20868888146697598,"open/intern-decision-4b":0.1395062328236417,"open/robojev-27b-v1@0.5":0.01276362610229595,"open/robojev-27b":null,"open/robojev-4b-v2":0.0032876614041202805,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.0023025600819802016,"open/robojev-4b-v3":0.0008535800184851479,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.17796679639807722,"respan/span-02":0.0451474,"typesafe/jev-1.13":0.24,"JEV-27B-VL (10 frames)":0.16539932636588014,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0078125}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000012","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000012","predictions":{"RoboJev-27B":0.007681558134561037,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.12721622924310436,"TypeSafe Jev 1.14":0.26,"Perplexity Decider":0.3535155932925217,"Liquid D1":0.11920291576401235,"Mercury Decide":0.46879062662624377,"Cloudflare Clef":0.2386,"cloudflare/clef-flash":0.1166,"cloudflare/clef-omni":0.0622,"liquid/d1-ultra":0.21695808790979365,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":0.038201795772077426,"open/robojev-27b":null,"open/robojev-4b-v2":0.0020145213081092066,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.0018155968873527504,"open/robojev-4b-v3":0.0006869178295131179,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.19643933369120614,"respan/span-02":0.067095675,"typesafe/jev-1.13":0.26,"JEV-27B-VL (10 frames)":0.12938674724490662,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.010009765625}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000014","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000014","predictions":{"RoboJev-27B":0.014594297222557551,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.039582947896527124,"TypeSafe Jev 1.14":0.33,"Perplexity Decider":0.3044918715177395,"Liquid D1":0.0850990542883219,"Mercury Decide":0.11920291263495983,"Cloudflare Clef":0.1843,"cloudflare/clef-flash":0.1042,"cloudflare/clef-omni":0.065,"liquid/d1-ultra":0.17794901006980235,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.0036638939388653003,"open/robojev-27b":null,"open/robojev-4b-v2":0.0017624512139676404,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.007144725422878838,"open/robojev-4b-v3@0.75":0.0019267347489025771,"open/robojev-4b-v3":0.0008084643262252317,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.17879578198775276,"respan/span-02":0.044230547,"typesafe/jev-1.13":0.27,"JEV-27B-VL (10 frames)":0.15121269659063727,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00360107421875}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000016","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000016","predictions":{"RoboJev-27B":0.006487505458910823,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.0877260673945944,"TypeSafe Jev 1.14":0.44,"Perplexity Decider":0.25940145894245437,"Liquid D1":0.30735801686526387,"Mercury Decide":0.06008665017400762,"Cloudflare Clef":0.3848,"cloudflare/clef-flash":0.1653,"cloudflare/clef-omni":0.0618,"liquid/d1-ultra":0.20065408285102265,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.00663256456339682,"open/robojev-27b":null,"open/robojev-4b-v2":0.0014746525778226533,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.009900079472737449,"open/robojev-4b-v3@0.75":0.006308531582070822,"open/robojev-4b-v3":0.0020341273969387797,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.1949972824202776,"respan/span-02":0.07502021,"typesafe/jev-1.13":0.46,"JEV-27B-VL (10 frames)":0.06655652832528444,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01068115234375}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000021","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000021","predictions":{"RoboJev-27B":0.993740156821979,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.8918888492928393,"TypeSafe Jev 1.14":0.82,"Perplexity Decider":0.9473666874641304,"Liquid D1":0.9706877707325846,"Mercury Decide":0.9959298629183346,"Cloudflare Clef":0.596,"cloudflare/clef-flash":0.8095,"cloudflare/clef-omni":0.2469,"liquid/d1-ultra":0.8727197320643494,"open/intern-decision-4b":0.8815938286018441,"open/robojev-27b-v1@0.5":0.9772498870236579,"open/robojev-27b":null,"open/robojev-4b-v2":0.994141165999323,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.9900999205272626,"open/robojev-4b-v3@0.75":0.9807077572950611,"open/robojev-4b-v3":0.9700628546674281,"openai/gpt-6-luna-decisions":0.92,"perplexity/pplx-decider-flash-v1.2":0.9385079965489783,"respan/span-02":0.87040955,"typesafe/jev-1.13":0.69,"JEV-27B-VL (10 frames)":0.7815208643730233,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.703125}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000022","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000022","predictions":{"RoboJev-27B":0.01408684024177201,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.045872819242022876,"TypeSafe Jev 1.14":0.36,"Perplexity Decider":0.26775000915691904,"Liquid D1":0.12592277139559055,"Mercury Decide":0.7549149923816048,"Cloudflare Clef":0.2104,"cloudflare/clef-flash":0.137,"cloudflare/clef-omni":0.0589,"liquid/d1-ultra":0.20065407152465806,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.003010559708344187,"open/robojev-27b":null,"open/robojev-4b-v2":0.005858834000676852,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.008141294289513608,"open/robojev-4b-v3@0.75":0.0021697908424400778,"open/robojev-4b-v3":0.0008084643262252317,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.11949887204718528,"respan/span-02":0.047146782,"typesafe/jev-1.13":0.19,"JEV-27B-VL (10 frames)":0.05951696892536981,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.010009765625}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000025","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000025","predictions":{"RoboJev-27B":0.008298200664150294,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.045872819242022876,"TypeSafe Jev 1.14":0.28,"Perplexity Decider":0.32768784006172896,"Liquid D1":0.16451644651115205,"Mercury Decide":0.32082130082460697,"Cloudflare Clef":0.2124,"cloudflare/clef-flash":0.0982,"cloudflare/clef-omni":0.0619,"liquid/d1-ultra":0.10691174302179939,"open/intern-decision-4b":0.13214384255458153,"open/robojev-27b-v1@0.5":0.006305727660984914,"open/robojev-27b":null,"open/robojev-4b-v2":0.001926734644431273,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.007626874902958847,"open/robojev-4b-v3@0.75":0.0017108587429636138,"open/robojev-4b-v3":0.000583634235945364,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.15781315700234672,"respan/span-02":0.029187884,"typesafe/jev-1.13":0.18,"JEV-27B-VL (10 frames)":0.07909487713844118,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01068115234375}},{"suite":"so101","id":"eye_drops_to_shelf/diffusion/eval_debug_task_cell_3_08h49m_25-jun-2026/ep000028","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000028","predictions":{"RoboJev-27B":0.006478763595652365,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.07947125509083774,"TypeSafe Jev 1.14":0.21,"Perplexity Decider":0.3978970560955493,"Liquid D1":0.22270012850745968,"Mercury Decide":0.2689414272294874,"Cloudflare Clef":0.1823,"cloudflare/clef-flash":0.1136,"cloudflare/clef-omni":0.0792,"liquid/d1-ultra":0.17794900662645485,"open/intern-decision-4b":0.1395062328236417,"open/robojev-27b-v1@0.5":0.003886775488571602,"open/robojev-27b":null,"open/robojev-4b-v2":0.003007688028932422,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.006269376036423619,"open/robojev-4b-v3@0.75":0.0023025600819802016,"open/robojev-4b-v3":0.0007657313877976473,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.18676854631835363,"respan/span-02":0.046710007,"typesafe/jev-1.13":0.2,"JEV-27B-VL (10 frames)":0.07791147619843489,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006683349609375}},{"suite":"so101","id":"eye_drops_to_shelf/molmoact2/eval_eye_drops_to_shelf_13h01m_08-jul-2026/ep000000","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000000","predictions":{"RoboJev-27B":0.01348623180935866,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.25818091441414076,"TypeSafe Jev 1.14":0.23,"Perplexity Decider":0.4062970915704894,"Liquid D1":0.2689414213699951,"Mercury Decide":0.0675466845698721,"Cloudflare Clef":0.2783,"cloudflare/clef-flash":0.2223,"cloudflare/clef-omni":0.0738,"liquid/d1-ultra":0.2813188325544226,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.061151938278927086,"open/robojev-27b":null,"open/robojev-4b-v2":0.002631674205642126,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.0037133326112963453,"open/robojev-4b-v3@0.75":0.0016121526329810115,"open/robojev-4b-v3":0.0006869178295131179,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1677938409798386,"respan/span-02":0.12542397,"typesafe/jev-1.13":0.2,"JEV-27B-VL (10 frames)":0.22777693046220276,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0284423828125}},{"suite":"so101","id":"eye_drops_to_shelf/molmoact2/eval_eye_drops_to_shelf_13h01m_08-jul-2026/ep000003","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000003","predictions":{"RoboJev-27B":0.0032467076480377738,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.1280738862408302,"TypeSafe Jev 1.14":0.24,"Perplexity Decider":0.2337526445513938,"Liquid D1":0.09534946232842245,"Mercury Decide":0.03308597493257518,"Cloudflare Clef":0.1969,"cloudflare/clef-flash":0.1543,"cloudflare/clef-omni":0.0676,"liquid/d1-ultra":0.31220407166527453,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.00011665893429831987,"open/robojev-27b":null,"open/robojev-4b-v2":0.004488287139460313,"open/robojev-4b-v3@0.25":0.007577240467071533,"open/robojev-4b-v3@0.5":0.0018042768835607238,"open/robojev-4b-v3@0.75":0.0010019928751388379,"open/robojev-4b-v3":0.0005527786044704864,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.09822093142956462,"respan/span-02":0.11707359,"typesafe/jev-1.13":0.27,"JEV-27B-VL (10 frames)":0.1781188448429793,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01361083984375}},{"suite":"so101","id":"eye_drops_to_shelf/molmoact2/eval_eye_drops_to_shelf_13h01m_08-jul-2026/ep000006","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000006","predictions":{"RoboJev-27B":0.006978731163856657,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.19265419510727433,"TypeSafe Jev 1.14":0.19,"Perplexity Decider":0.31791721367920794,"Liquid D1":0.22270013882530884,"Mercury Decide":0.18242552825126704,"Cloudflare Clef":0.2471,"cloudflare/clef-flash":0.2407,"cloudflare/clef-omni":0.0647,"liquid/d1-ultra":0.7085938448687948,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.010776238058007606,"open/robojev-27b":null,"open/robojev-4b-v2":0.003927901641619978,"open/robojev-4b-v3@0.25":0.01798621006309986,"open/robojev-4b-v3@0.5":0.002675199388665972,"open/robojev-4b-v3@0.75":0.0010019928751388379,"open/robojev-4b-v3":0.0006869178295131179,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.16277864585811433,"respan/span-02":0.098147675,"typesafe/jev-1.13":0.18,"JEV-27B-VL (10 frames)":0.16025700355966707,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.018798828125}},{"suite":"so101","id":"eye_drops_to_shelf/molmoact2/eval_eye_drops_to_shelf_13h01m_08-jul-2026/ep000008","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000008","predictions":{"RoboJev-27B":0.004454806768254864,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.032151010576124545,"TypeSafe Jev 1.14":0.14,"Perplexity Decider":0.08392267741484517,"Liquid D1":0.050330633309714545,"Mercury Decide":0.03308598136812592,"Cloudflare Clef":0.1713,"cloudflare/clef-flash":0.1016,"cloudflare/clef-omni":0.0921,"liquid/d1-ultra":0.14465801344268142,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.0010684796294987472,"open/robojev-27b":null,"open/robojev-4b-v2":0.002631674205642126,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.004825770646864498,"open/robojev-4b-v3@0.75":0.0027514904934948965,"open/robojev-4b-v3":0.0011822765498233803,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.07048508148544433,"respan/span-02":0.06685872,"typesafe/jev-1.13":0.2,"JEV-27B-VL (10 frames)":0.11688153043988099,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2080078125}},{"suite":"so101","id":"eye_drops_to_shelf/molmoact2/eval_eye_drops_to_shelf_13h01m_08-jul-2026/ep000009","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000009","predictions":{"RoboJev-27B":0.9961026496702219,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.7924827281261546,"TypeSafe Jev 1.14":0.81,"Perplexity Decider":0.9204229967515001,"Liquid D1":0.9937100989458286,"Mercury Decide":0.9959298617442528,"Cloudflare Clef":0.836,"cloudflare/clef-flash":0.7508,"cloudflare/clef-omni":0.2131,"liquid/d1-ultra":0.9319051045040039,"open/intern-decision-4b":0.8940776460411956,"open/robojev-27b-v1@0.5":0.995674591605225,"open/robojev-27b":null,"open/robojev-4b-v2":0.9870081646084733,"open/robojev-4b-v3@0.25":0.9924227595329285,"open/robojev-4b-v3@0.5":0.9954801073576106,"open/robojev-4b-v3@0.75":0.9940538504150612,"open/robojev-4b-v3":0.9921312523406053,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9726372076850727,"respan/span-02":0.94995344,"typesafe/jev-1.13":0.78,"JEV-27B-VL (10 frames)":0.8804178151730897,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0966796875}},{"suite":"so101","id":"eye_drops_to_shelf/molmoact2/eval_eye_drops_to_shelf_13h01m_08-jul-2026/ep000012","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000012","predictions":{"RoboJev-27B":0.008000765416238386,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.19871516808149167,"TypeSafe Jev 1.14":0.31,"Perplexity Decider":0.4088125369868689,"Liquid D1":0.4073334000459302,"Mercury Decide":0.18242553047372242,"Cloudflare Clef":0.241,"cloudflare/clef-flash":0.1109,"cloudflare/clef-omni":0.0539,"liquid/d1-ultra":0.39072106197134493,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.014627639712942444,"open/robojev-27b":null,"open/robojev-4b-v2":0.006692850868879798,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.007626874902958847,"open/robojev-4b-v3@0.75":0.0025929030441612317,"open/robojev-4b-v3":0.0009012109819517691,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1594456793305403,"respan/span-02":0.12925862,"typesafe/jev-1.13":0.32,"JEV-27B-VL (10 frames)":0.13507300797041524,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00830078125}},{"suite":"so101","id":"eye_drops_to_shelf/molmoact2/eval_eye_drops_to_shelf_13h01m_08-jul-2026/ep000013","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000013","predictions":{"RoboJev-27B":0.9954774067212397,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.9592105900733221,"TypeSafe Jev 1.14":0.81,"Perplexity Decider":0.968050554142287,"Liquid D1":0.9770226305917578,"Mercury Decide":0.9968273171678239,"Cloudflare Clef":0.8203,"cloudflare/clef-flash":0.762,"cloudflare/clef-omni":0.1016,"liquid/d1-ultra":0.8727197412158103,"open/intern-decision-4b":0.91062577829021,"open/robojev-27b-v1@0.5":0.9949751978606268,"open/robojev-27b":null,"open/robojev-4b-v2":0.9629926241583461,"open/robojev-4b-v3@0.25":0.9890130758285522,"open/robojev-4b-v3@0.5":0.9871579519028945,"open/robojev-4b-v3@0.75":0.9886181222715631,"open/robojev-4b-v3":0.9857848597914883,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9264359097444685,"respan/span-02":0.93776363,"typesafe/jev-1.13":0.85,"JEV-27B-VL (10 frames)":0.8455130625767597,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.4140625}},{"suite":"so101","id":"eye_drops_to_shelf/pi0.5/eval_debug_task_cell_3_14h49m_29-jun-2026/ep000002","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000002","predictions":{"RoboJev-27B":0.005523692010351988,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.0650573609569825,"TypeSafe Jev 1.14":0.13,"Perplexity Decider":0.022331156388996933,"Liquid D1":0.4073333856566001,"Mercury Decide":0.012431652568277681,"Cloudflare Clef":0.4005,"cloudflare/clef-flash":0.182,"cloudflare/clef-omni":0.0891,"liquid/d1-ultra":0.414461257641393,"open/intern-decision-4b":0.5777854893190272,"open/robojev-27b-v1@0.5":0.0059315533473621685,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016856305131264125,"open/robojev-4b-v3@0.25":0.009708477184176445,"open/robojev-4b-v3@0.5":0.0030502597001447,"open/robojev-4b-v3@0.75":0.0013488637996850762,"open/robojev-4b-v3":0.0007657313877976473,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.08411287691105923,"respan/span-02":0.86575145,"typesafe/jev-1.13":0.36,"JEV-27B-VL (10 frames)":0.05439921230648702,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.012451171875}},{"suite":"so101","id":"eye_drops_to_shelf/pi0.5/eval_debug_task_cell_3_14h49m_29-jun-2026/ep000005","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000005","predictions":{"RoboJev-27B":0.995025000193384,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.859336927174997,"TypeSafe Jev 1.14":0.64,"Perplexity Decider":0.8250420273321967,"Liquid D1":0.9755769092358045,"Mercury Decide":0.9525741318713181,"Cloudflare Clef":0.8999,"cloudflare/clef-flash":0.6822,"cloudflare/clef-omni":0.2093,"liquid/d1-ultra":0.8360373935955678,"open/intern-decision-4b":0.9248060506082927,"open/robojev-27b-v1@0.5":0.9826703350280453,"open/robojev-27b":null,"open/robojev-4b-v2":0.9923553212886647,"open/robojev-4b-v3@0.25":0.9890130758285522,"open/robojev-4b-v3@0.5":0.9913098936809337,"open/robojev-4b-v3@0.75":0.9871976056650185,"open/robojev-4b-v3":0.9782115888298761,"openai/gpt-6-luna-decisions":0.66,"perplexity/pplx-decider-flash-v1.2":0.9304544912024579,"respan/span-02":0.94803035,"typesafe/jev-1.13":0.72,"JEV-27B-VL (10 frames)":0.8140083246009729,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.578125}},{"suite":"so101","id":"eye_drops_to_shelf/pi0.5/eval_debug_task_cell_3_14h49m_29-jun-2026/ep000006","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000006","predictions":{"RoboJev-27B":0.9934699675150135,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.7768718518621963,"TypeSafe Jev 1.14":0.65,"Perplexity Decider":0.9316390687420745,"Liquid D1":0.9770226287518852,"Mercury Decide":0.9924227574785333,"Cloudflare Clef":0.8532,"cloudflare/clef-flash":0.6609,"cloudflare/clef-omni":0.1003,"liquid/d1-ultra":0.8071467619137317,"open/intern-decision-4b":0.8748864949022742,"open/robojev-27b-v1@0.5":0.9321003475004644,"open/robojev-27b":null,"open/robojev-4b-v2":0.9923553212886647,"open/robojev-4b-v3@0.25":0.9875683188438416,"open/robojev-4b-v3@0.5":0.9913098936809337,"open/robojev-4b-v3@0.75":0.9879284859685241,"open/robojev-4b-v3":0.9782115888298761,"openai/gpt-6-luna-decisions":0.89,"perplexity/pplx-decider-flash-v1.2":0.8662157538286727,"respan/span-02":0.5813811,"typesafe/jev-1.13":0.63,"JEV-27B-VL (10 frames)":0.8533721395892151,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.32421875}},{"suite":"so101","id":"eye_drops_to_shelf/pi0.5/eval_debug_task_cell_3_14h49m_29-jun-2026/ep000008","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000008","predictions":{"RoboJev-27B":0.994345175357303,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.9052118373829948,"TypeSafe Jev 1.14":0.7,"Perplexity Decider":0.8162750474748881,"Liquid D1":0.9724147201714924,"Mercury Decide":0.9875683471916095,"Cloudflare Clef":0.7552,"cloudflare/clef-flash":0.7675,"cloudflare/clef-omni":0.3067,"liquid/d1-ultra":0.8291577931942526,"open/intern-decision-4b":0.9156019658234928,"open/robojev-27b-v1@0.5":0.9778727801032849,"open/robojev-27b":null,"open/robojev-4b-v2":0.9916473246952838,"open/robojev-4b-v3@0.25":0.9902915358543396,"open/robojev-4b-v3@0.5":0.9918587057104864,"open/robojev-4b-v3@0.75":0.9828358483253791,"open/robojev-4b-v3":0.9744517038899213,"openai/gpt-6-luna-decisions":0.64,"perplexity/pplx-decider-flash-v1.2":0.9488879698304885,"respan/span-02":0.8086903,"typesafe/jev-1.13":0.74,"JEV-27B-VL (10 frames)":0.7988305339924621,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.10986328125}},{"suite":"so101","id":"eye_drops_to_shelf/pi0.5/eval_debug_task_cell_3_14h49m_29-jun-2026/ep000010","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000010","predictions":{"RoboJev-27B":0.007842675187829601,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.08291840757852213,"TypeSafe Jev 1.14":0.24,"Perplexity Decider":0.07754838434349091,"Liquid D1":0.6513548782017746,"Mercury Decide":0.014063627120726901,"Cloudflare Clef":0.2572,"cloudflare/clef-flash":0.2998,"cloudflare/clef-omni":0.0684,"liquid/d1-ultra":0.30170334764715173,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.006170591519440673,"open/robojev-27b":null,"open/robojev-4b-v2":0.0046922355486094065,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.013703364243695216,"open/robojev-4b-v3@0.75":0.0030982660175204184,"open/robojev-4b-v3":0.0012482263663496401,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.19566296545007253,"respan/span-02":0.33688018,"typesafe/jev-1.13":0.37,"JEV-27B-VL (10 frames)":0.01854088732094487,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.058349609375}},{"suite":"so101","id":"eye_drops_to_shelf/pi0.5/eval_debug_task_cell_3_14h49m_29-jun-2026/ep000013","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000013","predictions":{"RoboJev-27B":0.9951441694031213,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":0.9134616520026637,"TypeSafe Jev 1.14":0.64,"Perplexity Decider":0.9181105292142437,"Liquid D1":0.9324533022906132,"Mercury Decide":0.9840936103583101,"Cloudflare Clef":0.8619,"cloudflare/clef-flash":0.5921,"cloudflare/clef-omni":0.1362,"liquid/d1-ultra":0.8147146268461545,"open/intern-decision-4b":0.9248060506082927,"open/robojev-27b-v1@0.5":0.9921784544706896,"open/robojev-27b":null,"open/robojev-4b-v2":0.7532592839990138,"open/robojev-4b-v3@0.25":0.9875683188438416,"open/robojev-4b-v3@0.5":0.9894338107727867,"open/robojev-4b-v3@0.75":0.9756477227346713,"open/robojev-4b-v3":0.9278650639695798,"openai/gpt-6-luna-decisions":0.86,"perplexity/pplx-decider-flash-v1.2":0.8709374677466345,"respan/span-02":0.78147614,"typesafe/jev-1.13":0.73,"JEV-27B-VL (10 frames)":0.9139100480048228,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.12255859375}},{"suite":"so101","id":"eye_drops_to_shelf/pi0/eval_debug_task_cell_3_13h52m_29-jun-2026/ep000000","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000000","predictions":{"RoboJev-27B":0.005586496318313977,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.05428094209809575,"TypeSafe Jev 1.14":0.15,"Perplexity Decider":0.05127044658642523,"Liquid D1":0.7662936430859597,"Mercury Decide":0.022977369659133905,"Cloudflare Clef":0.2052,"cloudflare/clef-flash":0.1723,"cloudflare/clef-omni":0.0696,"liquid/d1-ultra":0.3560898041822152,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.0025183182800048768,"open/robojev-27b":null,"open/robojev-4b-v2":0.002751490629587489,"open/robojev-4b-v3@0.25":0.008577484637498856,"open/robojev-4b-v3@0.5":0.002197092076271529,"open/robojev-4b-v3@0.75":0.0010019928751388379,"open/robojev-4b-v3":0.000583634235945364,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1788554408266718,"respan/span-02":0.12206441,"typesafe/jev-1.13":0.33,"JEV-27B-VL (10 frames)":0.04452742284217653,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0260009765625}},{"suite":"so101","id":"eye_drops_to_shelf/pi0/eval_debug_task_cell_3_13h52m_29-jun-2026/ep000007","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000007","predictions":{"RoboJev-27B":0.9956569477285391,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.9407478539726559,"TypeSafe Jev 1.14":0.74,"Perplexity Decider":0.9428833462256014,"Liquid D1":0.9928785723869046,"Mercury Decide":0.9959298632467755,"Cloudflare Clef":0.875,"cloudflare/clef-flash":0.7555,"cloudflare/clef-omni":0.2791,"liquid/d1-ultra":0.8291577965286618,"open/intern-decision-4b":0.8748864949022742,"open/robojev-27b-v1@0.5":0.9899627504589347,"open/robojev-27b":null,"open/robojev-4b-v2":0.9030990470024011,"open/robojev-4b-v3@0.25":0.9875683188438416,"open/robojev-4b-v3@0.5":0.9913098936809337,"open/robojev-4b-v3@0.75":0.9871976056650185,"open/robojev-4b-v3":0.9814286862202798,"openai/gpt-6-luna-decisions":0.91,"perplexity/pplx-decider-flash-v1.2":0.8839916617923316,"respan/span-02":0.32902429,"typesafe/jev-1.13":0.76,"JEV-27B-VL (10 frames)":0.8443519835157492,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.193359375}},{"suite":"so101","id":"eye_drops_to_shelf/pi0/eval_debug_task_cell_3_13h52m_29-jun-2026/ep000008","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000008","predictions":{"RoboJev-27B":0.9948086532490372,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.8769477823922106,"TypeSafe Jev 1.14":0.72,"Perplexity Decider":0.8825007676165221,"Liquid D1":0.9783846674737009,"Mercury Decide":0.9770226320134775,"Cloudflare Clef":0.849,"cloudflare/clef-flash":0.744,"cloudflare/clef-omni":0.1807,"liquid/d1-ultra":0.8071467765700858,"open/intern-decision-4b":0.9203253283037116,"open/robojev-27b-v1@0.5":0.9880071282460792,"open/robojev-27b":null,"open/robojev-4b-v2":0.9891096552016757,"open/robojev-4b-v3@0.25":0.9890130758285522,"open/robojev-4b-v3@0.5":0.9907244334212516,"open/robojev-4b-v3@0.75":0.9864230820189066,"open/robojev-4b-v3":0.9757703987213749,"openai/gpt-6-luna-decisions":0.9,"perplexity/pplx-decider-flash-v1.2":0.8742960341163839,"respan/span-02":0.9052532,"typesafe/jev-1.13":0.72,"JEV-27B-VL (10 frames)":0.8340144585551353,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0284423828125}},{"suite":"so101","id":"eye_drops_to_shelf/pi0/eval_debug_task_cell_3_13h52m_29-jun-2026/ep000010","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000010","predictions":{"RoboJev-27B":0.9934183254817048,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.8834440806162303,"TypeSafe Jev 1.14":0.65,"Perplexity Decider":0.9604997368280819,"Liquid D1":0.9908743624760779,"Mercury Decide":0.9902915233842168,"Cloudflare Clef":0.8607,"cloudflare/clef-flash":0.7954,"cloudflare/clef-omni":0.1796,"liquid/d1-ultra":0.8147146268461545,"open/intern-decision-4b":0.8815938286018441,"open/robojev-27b-v1@0.5":0.9887858849228537,"open/robojev-27b":null,"open/robojev-4b-v2":0.9912693183717645,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.9907244334212516,"open/robojev-4b-v3@0.75":0.9856023867504186,"open/robojev-4b-v3":0.9793403302916414,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9129512362748846,"respan/span-02":0.16146919,"typesafe/jev-1.13":0.62,"JEV-27B-VL (10 frames)":0.8065208773029691,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.392578125}},{"suite":"so101","id":"eye_drops_to_shelf/pi0/eval_debug_task_cell_3_13h52m_29-jun-2026/ep000012","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000012","predictions":{"RoboJev-27B":0.9963271663533219,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.9187866238758687,"TypeSafe Jev 1.14":0.72,"Perplexity Decider":0.9592990228784479,"Liquid D1":0.9961755172353178,"Mercury Decide":0.9947798731118894,"Cloudflare Clef":0.8714,"cloudflare/clef-flash":0.624,"cloudflare/clef-omni":0.1814,"liquid/d1-ultra":0.8491262276507164,"open/intern-decision-4b":0.8940776460411956,"open/robojev-27b-v1@0.5":0.9922918944817707,"open/robojev-27b":null,"open/robojev-4b-v2":0.9881046720916962,"open/robojev-4b-v3@0.25":0.9902915358543396,"open/robojev-4b-v3@0.5":0.9923731250970411,"open/robojev-4b-v3@0.75":0.9886181222715631,"open/robojev-4b-v3":0.9757703987213749,"openai/gpt-6-luna-decisions":0.87,"perplexity/pplx-decider-flash-v1.2":0.9235204088403377,"respan/span-02":0.7532084,"typesafe/jev-1.13":0.65,"JEV-27B-VL (10 frames)":0.8909941288988424,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.19921875}},{"suite":"so101","id":"eye_drops_to_shelf/pi0/eval_debug_task_cell_3_13h52m_29-jun-2026/ep000013","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000013","predictions":{"RoboJev-27B":0.9893391168656775,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.92,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.8692698721717443,"TypeSafe Jev 1.14":0.62,"Perplexity Decider":0.9343695812001424,"Liquid D1":0.9875683519824322,"Mercury Decide":0.9940889318551904,"Cloudflare Clef":0.808,"cloudflare/clef-flash":0.6876,"cloudflare/clef-omni":0.2712,"liquid/d1-ultra":0.7658012615387644,"open/intern-decision-4b":0.8678561574454184,"open/robojev-27b-v1@0.5":0.9583806676020576,"open/robojev-27b":null,"open/robojev-4b-v2":0.9886181217784766,"open/robojev-4b-v3@0.25":0.9840936064720154,"open/robojev-4b-v3@0.5":0.9862966357563048,"open/robojev-4b-v3@0.75":0.9726532127177251,"open/robojev-4b-v3":0.9568029835538762,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.8756607831828582,"respan/span-02":0.8618201,"typesafe/jev-1.13":0.64,"JEV-27B-VL (10 frames)":0.8265444462765688,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.333984375}},{"suite":"so101","id":"eye_drops_to_shelf/pi0/eval_debug_task_cell_3_13h52m_29-jun-2026/ep000016","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000016","predictions":{"RoboJev-27B":0.9941309153096417,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.8948238627857265,"TypeSafe Jev 1.14":0.62,"Perplexity Decider":0.8955777620171975,"Liquid D1":0.964855153093913,"Mercury Decide":0.9902915212889941,"Cloudflare Clef":0.9154,"cloudflare/clef-flash":0.7416,"cloudflare/clef-omni":0.279,"liquid/d1-ultra":0.8071467765700858,"open/intern-decision-4b":0.9203253283037116,"open/robojev-27b-v1@0.5":0.9901259092934941,"open/robojev-27b":null,"open/robojev-4b-v2":0.9726532135583835,"open/robojev-4b-v3@0.25":0.9890130758285522,"open/robojev-4b-v3@0.5":0.9928552745771213,"open/robojev-4b-v3@0.75":0.9879284859685241,"open/robojev-4b-v3":0.9770226297071284,"openai/gpt-6-luna-decisions":0.73,"perplexity/pplx-decider-flash-v1.2":0.9384536248172721,"respan/span-02":0.9486883,"typesafe/jev-1.13":0.61,"JEV-27B-VL (10 frames)":0.7964137598533279,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.67578125}},{"suite":"so101","id":"eye_drops_to_shelf/pi0/eval_debug_task_cell_3_13h52m_29-jun-2026/ep000017","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000017","predictions":{"RoboJev-27B":0.9962570428653447,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":0.9290585483310958,"TypeSafe Jev 1.14":0.63,"Perplexity Decider":0.9316587146543998,"Liquid D1":0.9433475746920261,"Mercury Decide":0.9902915242527492,"Cloudflare Clef":0.8139,"cloudflare/clef-flash":0.6224,"cloudflare/clef-omni":0.2112,"liquid/d1-ultra":0.8147146268461545,"open/intern-decision-4b":0.8879876242264044,"open/robojev-27b-v1@0.5":0.9919161938306843,"open/robojev-27b":null,"open/robojev-4b-v2":0.9521691293545035,"open/robojev-4b-v3@0.25":0.9890130758285522,"open/robojev-4b-v3@0.5":0.9913098936809337,"open/robojev-4b-v3@0.75":0.9847328451036568,"open/robojev-4b-v3":0.9684435763811455,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9112780655291278,"respan/span-02":0.9431192,"typesafe/jev-1.13":0.67,"JEV-27B-VL (10 frames)":0.9012949056896686,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.72265625}},{"suite":"so101","id":"eye_drops_to_shelf/pi0/eval_debug_task_cell_3_13h52m_29-jun-2026/ep000020","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000020","predictions":{"RoboJev-27B":0.9963600826451553,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.9444958509958956,"TypeSafe Jev 1.14":0.71,"Perplexity Decider":0.874392428731882,"Liquid D1":0.9820137868795701,"Mercury Decide":0.9933071480355454,"Cloudflare Clef":0.907,"cloudflare/clef-flash":0.7927,"cloudflare/clef-omni":0.3364,"liquid/d1-ultra":0.8491262080493697,"open/intern-decision-4b":0.91062577829021,"open/robojev-27b-v1@0.5":0.994029091997126,"open/robojev-27b":null,"open/robojev-4b-v2":0.8991213731853014,"open/robojev-4b-v3@0.25":0.9890130758285522,"open/robojev-4b-v3@0.5":0.9894338107727867,"open/robojev-4b-v3@0.75":0.9807077572950611,"open/robojev-4b-v3":0.9589942930045862,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9127179764716092,"respan/span-02":0.9393231,"typesafe/jev-1.13":0.71,"JEV-27B-VL (10 frames)":0.9001663581718337,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.5390625}},{"suite":"so101","id":"eye_drops_to_shelf/pi0/eval_debug_task_cell_3_13h52m_29-jun-2026/ep000024","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000024","predictions":{"RoboJev-27B":0.9952375237521478,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.8940967838892754,"TypeSafe Jev 1.14":0.48,"Perplexity Decider":0.9472421019447,"Liquid D1":0.9908743638908653,"Mercury Decide":0.9914225141190147,"Cloudflare Clef":0.6986,"cloudflare/clef-flash":0.6816,"cloudflare/clef-omni":0.0713,"liquid/d1-ultra":0.7658012573170664,"open/intern-decision-4b":0.799028310455341,"open/robojev-27b-v1@0.5":0.9821001791848252,"open/robojev-27b":null,"open/robojev-4b-v2":0.9904617115703054,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.9907244334212516,"open/robojev-4b-v3@0.75":0.9818023083761724,"open/robojev-4b-v3":0.963061736331977,"openai/gpt-6-luna-decisions":0.93,"perplexity/pplx-decider-flash-v1.2":0.902243644724227,"respan/span-02":0.8067587,"typesafe/jev-1.13":0.74,"JEV-27B-VL (10 frames)":0.8515024636182983,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.478515625}},{"suite":"so101","id":"eye_drops_to_shelf/pi0/eval_debug_task_cell_3_13h52m_29-jun-2026/ep000025","task":"Put the eye drops on the shelf","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000025","predictions":{"RoboJev-27B":0.9955785154748532,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.8997911640795737,"TypeSafe Jev 1.14":0.73,"Perplexity Decider":0.8922969320486953,"Liquid D1":0.9875683507933021,"Mercury Decide":0.9859363761593198,"Cloudflare Clef":0.8414,"cloudflare/clef-flash":0.6834,"cloudflare/clef-omni":0.2149,"liquid/d1-ultra":0.8613434933623686,"open/intern-decision-4b":0.9053865123447689,"open/robojev-27b-v1@0.5":0.9922521488793867,"open/robojev-27b":null,"open/robojev-4b-v2":0.9895801834005146,"open/robojev-4b-v3@0.25":0.9902915358543396,"open/robojev-4b-v3@0.5":0.9928552745771213,"open/robojev-4b-v3@0.75":0.9892687880395139,"open/robojev-4b-v3":0.9814286862202798,"openai/gpt-6-luna-decisions":0.92,"perplexity/pplx-decider-flash-v1.2":0.9076003012543669,"respan/span-02":0.9181175,"typesafe/jev-1.13":0.75,"JEV-27B-VL (10 frames)":0.8662393050530605,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.5625}},{"suite":"so101","id":"eye_drops_to_shelf/pi0/eval_debug_task_cell_3_13h52m_29-jun-2026/ep000026","task":"Put the eye drops on the shelf","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"eye_drops_to_shelf","episode":"ep000026","predictions":{"RoboJev-27B":0.004767251601515337,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.0596564514973722,"TypeSafe Jev 1.14":0.2,"Perplexity Decider":0.053727402729626506,"Liquid D1":0.2814055953761018,"Mercury Decide":0.017986209271205138,"Cloudflare Clef":0.2043,"cloudflare/clef-flash":0.1297,"cloudflare/clef-omni":0.072,"liquid/d1-ultra":0.21695808790979365,"open/intern-decision-4b":0.5930110454411601,"open/robojev-27b-v1@0.5":0.004007508589278521,"open/robojev-27b":null,"open/robojev-4b-v2":0.0017624512139676404,"open/robojev-4b-v3@0.25":0.007577240467071533,"open/robojev-4b-v3@0.5":0.0019267347052741358,"open/robojev-4b-v3@0.75":0.00078986592964705,"open/robojev-4b-v3":0.0004696544949846406,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.14099760926829585,"respan/span-02":0.14641042,"typesafe/jev-1.13":0.41,"JEV-27B-VL (10 frames)":0.04479100699472883,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01495361328125}},{"suite":"so101","id":"ring_insert/act/eval_debug_task_cell_1_12h18m_26-jun-2026/ep000007","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000007","predictions":{"RoboJev-27B":0.020484624898070555,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.015202041221705266,"TypeSafe Jev 1.14":0.07,"Perplexity Decider":0.049567520444135524,"Liquid D1":0.11279539733570562,"Mercury Decide":0.006692850689008419,"Cloudflare Clef":0.2483,"cloudflare/clef-flash":0.2644,"cloudflare/clef-omni":0.0951,"liquid/d1-ultra":0.18528537670715625,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.005282750144823827,"open/robojev-27b":null,"open/robojev-4b-v2":0.06424971190493048,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.01560037702180545,"open/robojev-4b-v3@0.75":0.007990902377034759,"open/robojev-4b-v3":0.006007651396687169,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.5025708448829733,"respan/span-02":0.098218605,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.011902033827229439,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0306396484375}},{"suite":"so101","id":"ring_insert/act/eval_debug_task_cell_1_12h18m_26-jun-2026/ep000012","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000012","predictions":{"RoboJev-27B":0.9959173648394842,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.938118768049889,"TypeSafe Jev 1.14":0.83,"Perplexity Decider":0.9391429312675543,"Liquid D1":0.9724147207710628,"Mercury Decide":0.46879062662624377,"Cloudflare Clef":0.8855,"cloudflare/clef-flash":0.8268,"cloudflare/clef-omni":0.6154,"liquid/d1-ultra":0.9865432739174573,"open/intern-decision-4b":0.8748864949022742,"open/robojev-27b-v1@0.5":0.9927545438629054,"open/robojev-27b":null,"open/robojev-4b-v2":0.04990557889898353,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.9662767595980272,"open/robojev-4b-v3@0.75":0.93575028740662,"open/robojev-4b-v3":0.9027587968854268,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.9650231374679227,"respan/span-02":0.930558,"typesafe/jev-1.13":0.83,"JEV-27B-VL (10 frames)":0.966333372726123,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.8984375}},{"suite":"so101","id":"ring_insert/act/eval_debug_task_cell_1_12h27m_26-jun-2026/ep000002","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000002","predictions":{"RoboJev-27B":0.9584220150895757,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.8437709155223931,"TypeSafe Jev 1.14":0.42,"Perplexity Decider":0.10593342792636536,"Liquid D1":0.8354835371034369,"Mercury Decide":0.04208772896694963,"Cloudflare Clef":0.5488,"cloudflare/clef-flash":0.6442,"cloudflare/clef-omni":0.0812,"liquid/d1-ultra":0.8220509985385663,"open/intern-decision-4b":0.3201997500236374,"open/robojev-27b-v1@0.5":0.9872923575623337,"open/robojev-27b":null,"open/robojev-4b-v2":0.10927050321483402,"open/robojev-4b-v3@0.25":0.8354835510253906,"open/robojev-4b-v3@0.5":0.9035094985644659,"open/robojev-4b-v3@0.75":0.8245695962243903,"open/robojev-4b-v3":0.6696321275705963,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.10327282132499849,"respan/span-02":0.078177765,"typesafe/jev-1.13":0.49,"JEV-27B-VL (10 frames)":0.8354207528779228,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.703125}},{"suite":"so101","id":"ring_insert/act/eval_debug_task_cell_1_12h27m_26-jun-2026/ep000007","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000007","predictions":{"RoboJev-27B":0.0064182830444949966,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.005203673546061658,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.011582618577315447,"Liquid D1":0.02931222905542399,"Mercury Decide":0.0015978456507620572,"Cloudflare Clef":0.095,"cloudflare/clef-flash":0.1673,"cloudflare/clef-omni":0.0745,"liquid/d1-ultra":0.04917794911560182,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.0015900886744173,"open/robojev-27b":null,"open/robojev-4b-v2":0.042087729958985645,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.0027514904934948965,"open/robojev-4b-v3":0.0012482263663496401,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.06100847094155535,"respan/span-02":0.059168402,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.001376701566566612,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1396484375}},{"suite":"so101","id":"ring_insert/grootn1.7/eval_debug_task_cell_1_16h34m_27-jun-2026/ep000003","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000003","predictions":{"RoboJev-27B":0.9897480342542072,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.6152894211454202,"TypeSafe Jev 1.14":0.62,"Perplexity Decider":0.42111003982809364,"Liquid D1":0.9241418220680101,"Mercury Decide":0.0850990490675896,"Cloudflare Clef":0.6748,"cloudflare/clef-flash":0.7715,"cloudflare/clef-omni":0.4984,"liquid/d1-ultra":0.9218847297799232,"open/intern-decision-4b":0.7557061813028185,"open/robojev-27b-v1@0.5":0.8594451762066035,"open/robojev-27b":null,"open/robojev-4b-v2":0.07278720919427024,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.07585817666120565,"open/robojev-4b-v3@0.75":0.038631651048510164,"open/robojev-4b-v3":0.03505281632584716,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.5522388258977763,"respan/span-02":0.10221473,"typesafe/jev-1.13":0.75,"JEV-27B-VL (10 frames)":0.7756543431076954,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.77734375}},{"suite":"so101","id":"ring_insert/grootn1.7/eval_debug_task_cell_1_16h34m_27-jun-2026/ep000004","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000004","predictions":{"RoboJev-27B":0.9950591758128965,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.6457797739167208,"TypeSafe Jev 1.14":0.83,"Perplexity Decider":0.6486819809955342,"Liquid D1":0.9579122732859019,"Mercury Decide":0.10669060175672705,"Cloudflare Clef":0.87,"cloudflare/clef-flash":0.8889,"cloudflare/clef-omni":0.3727,"liquid/d1-ultra":0.7085938448687948,"open/intern-decision-4b":0.8879876242264044,"open/robojev-27b-v1@0.5":0.9427141014553283,"open/robojev-27b":null,"open/robojev-4b-v2":0.12300397797247992,"open/robojev-4b-v3@0.25":0.970687747001648,"open/robojev-4b-v3@0.5":0.9241418233387945,"open/robojev-4b-v3@0.75":0.7668262163944938,"open/robojev-4b-v3":0.367378816897974,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.7875309393997506,"respan/span-02":0.26637143,"typesafe/jev-1.13":0.66,"JEV-27B-VL (10 frames)":0.9637543302628738,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.93359375}},{"suite":"so101","id":"ring_insert/grootn1.7/eval_debug_task_cell_1_16h34m_27-jun-2026/ep000006","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000006","predictions":{"RoboJev-27B":0.9782125257060847,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.7,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.09742337819726668,"TypeSafe Jev 1.14":0.13,"Perplexity Decider":0.10586886364614743,"Liquid D1":0.29421497216298875,"Mercury Decide":0.025957359882173466,"Cloudflare Clef":0.3581,"cloudflare/clef-flash":0.377,"cloudflare/clef-omni":0.1684,"liquid/d1-ultra":0.39072106197134493,"open/intern-decision-4b":0.5313278281391198,"open/robojev-27b-v1@0.5":0.024448568891878325,"open/robojev-27b":null,"open/robojev-4b-v2":0.02618406111961536,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.04924136119799765,"open/robojev-4b-v3@0.75":0.02167836395087896,"open/robojev-4b-v3":0.009249319533522623,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.21104008686460324,"respan/span-02":0.10286889,"typesafe/jev-1.13":0.2,"JEV-27B-VL (10 frames)":0.8627488492983402,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.5234375}},{"suite":"so101","id":"ring_insert/grootn1.7/eval_debug_task_cell_1_16h34m_27-jun-2026/ep000007","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000007","predictions":{"RoboJev-27B":0.9859629662138834,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.68,"JEV-27B-VL":0.7387666904035424,"TypeSafe Jev 1.14":0.54,"Perplexity Decider":0.35547833406544377,"Liquid D1":0.988312743295193,"Mercury Decide":0.08509904964767095,"Cloudflare Clef":0.7843,"cloudflare/clef-flash":0.6925,"cloudflare/clef-omni":0.1296,"liquid/d1-ultra":0.8727197438305133,"open/intern-decision-4b":0.4069889545588398,"open/robojev-27b-v1@0.5":0.9607018336732785,"open/robojev-27b":null,"open/robojev-4b-v2":0.10927050321483402,"open/robojev-4b-v3@0.25":0.18242551386356354,"open/robojev-4b-v3@0.5":0.1292175522858696,"open/robojev-4b-v3@0.75":0.1107273107211166,"open/robojev-4b-v3":0.08810813794451551,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.2169876499800097,"respan/span-02":0.17631675,"typesafe/jev-1.13":0.8,"JEV-27B-VL (10 frames)":0.8073158053297909,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.80859375}},{"suite":"so101","id":"ring_insert/grootn1.7/eval_debug_task_cell_1_16h34m_27-jun-2026/ep000009","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000009","predictions":{"RoboJev-27B":0.004283002700985614,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.00620595045720397,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.028213416503325605,"Liquid D1":0.2942149597859341,"Mercury Decide":0.006692851221476155,"Cloudflare Clef":0.4476,"cloudflare/clef-flash":0.2439,"cloudflare/clef-omni":0.2504,"liquid/d1-ultra":0.0515382696634073,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.0007490993228711857,"open/robojev-27b":null,"open/robojev-4b-v2":0.005858834000676852,"open/robojev-4b-v3@0.25":0.01098694372922182,"open/robojev-4b-v3@0.5":0.0030502597001447,"open/robojev-4b-v3@0.75":0.0021697908424400778,"open/robojev-4b-v3":0.0020341273969387797,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.028953080737481,"respan/span-02":0.052630648,"typesafe/jev-1.13":0.15,"JEV-27B-VL (10 frames)":0.010251797391758598,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2021484375}},{"suite":"so101","id":"ring_insert/grootn1.7/eval_debug_task_cell_1_16h34m_27-jun-2026/ep000019","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000019","predictions":{"RoboJev-27B":0.9926326372367598,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.6387010457123248,"TypeSafe Jev 1.14":0.86,"Perplexity Decider":0.35659980931479407,"Liquid D1":0.9961755165114838,"Mercury Decide":0.07585817740967664,"Cloudflare Clef":0.7984,"cloudflare/clef-flash":0.7601,"cloudflare/clef-omni":0.1129,"liquid/d1-ultra":0.9218847357128244,"open/intern-decision-4b":0.6659927647326706,"open/robojev-27b-v1@0.5":0.9066402848716512,"open/robojev-27b":null,"open/robojev-4b-v2":0.042087729958985645,"open/robojev-4b-v3@0.25":0.9740425944328308,"open/robojev-4b-v3@0.5":0.4025775341117646,"open/robojev-4b-v3@0.75":0.1754304037756096,"open/robojev-4b-v3":0.13612834674424493,"openai/gpt-6-luna-decisions":0.26,"perplexity/pplx-decider-flash-v1.2":0.5621415255456337,"respan/span-02":0.08323689,"typesafe/jev-1.13":0.77,"JEV-27B-VL (10 frames)":0.9171076843165911,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.7578125}},{"suite":"so101","id":"ring_insert/grootn1.7/eval_debug_task_cell_1_16h34m_27-jun-2026/ep000022","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000022","predictions":{"RoboJev-27B":0.9822609147270862,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.75,"JEV-27B-VL":0.656278465587415,"TypeSafe Jev 1.14":0.6,"Perplexity Decider":0.2481267093090801,"Liquid D1":0.9241418252018903,"Mercury Decide":0.29421496597446145,"Cloudflare Clef":0.6377,"cloudflare/clef-flash":0.5756,"cloudflare/clef-omni":0.3052,"liquid/d1-ultra":0.7186811674455774,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.6006957315998654,"open/robojev-27b":null,"open/robojev-4b-v2":0.23052358465184783,"open/robojev-4b-v3@0.25":0.22270014882087708,"open/robojev-4b-v3@0.5":0.102380250911392,"open/robojev-4b-v3@0.75":0.07585818674635426,"open/robojev-4b-v3":0.04100570699541391,"openai/gpt-6-luna-decisions":0.17,"perplexity/pplx-decider-flash-v1.2":0.4170305647047126,"respan/span-02":0.1409296,"typesafe/jev-1.13":0.49,"JEV-27B-VL (10 frames)":0.9005398236244111,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.7265625}},{"suite":"so101","id":"ring_insert/grootn1.7/eval_debug_task_cell_1_16h34m_27-jun-2026/ep000026","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000026","predictions":{"RoboJev-27B":0.01059732288202982,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.01879217761831776,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.037887246580351995,"Liquid D1":0.32082130082460697,"Mercury Decide":0.007577240469475037,"Cloudflare Clef":0.3542,"cloudflare/clef-flash":0.2923,"cloudflare/clef-omni":0.2018,"liquid/d1-ultra":0.14465800616138325,"open/intern-decision-4b":0.42221451068097277,"open/robojev-27b-v1@0.5":0.001683090576334184,"open/robojev-27b":null,"open/robojev-4b-v2":0.016188347137528064,"open/robojev-4b-v3@0.25":0.022977370768785477,"open/robojev-4b-v3@0.5":0.005872534859081002,"open/robojev-4b-v3@0.75":0.0041678002213721265,"open/robojev-4b-v3":0.0025268270309959213,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.11420523547058278,"respan/span-02":0.1294485,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.011641951987634033,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.50390625}},{"suite":"so101","id":"ring_insert/grootn1.7/eval_debug_task_cell_1_16h34m_27-jun-2026/ep000027","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000027","predictions":{"RoboJev-27B":0.9951905163729917,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.9158662608975009,"TypeSafe Jev 1.14":0.82,"Perplexity Decider":0.6421132275001679,"Liquid D1":0.9525741231199173,"Mercury Decide":0.9706877690366521,"Cloudflare Clef":0.7811,"cloudflare/clef-flash":0.8595,"cloudflare/clef-omni":0.1646,"liquid/d1-ultra":0.9721927618963851,"open/intern-decision-4b":0.7557061813028185,"open/robojev-27b-v1@0.5":0.9907160187576854,"open/robojev-27b":null,"open/robojev-4b-v2":0.059086031855120416,"open/robojev-4b-v3@0.25":0.9669140577316284,"open/robojev-4b-v3@0.5":0.9565659184411002,"open/robojev-4b-v3@0.75":0.948664203960477,"open/robojev-4b-v3":0.8573531996579977,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.8979967122681655,"respan/span-02":0.89308685,"typesafe/jev-1.13":0.64,"JEV-27B-VL (10 frames)":0.9700324941304347,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.93359375}},{"suite":"so101","id":"ring_insert/grootn1.7/eval_debug_task_cell_1_16h34m_27-jun-2026/ep000029","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000029","predictions":{"RoboJev-27B":0.009117419906700907,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.011607404058322229,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.024996532346367645,"Liquid D1":0.04742587082142043,"Mercury Decide":0.0015978453454441694,"Cloudflare Clef":0.1279,"cloudflare/clef-flash":0.2156,"cloudflare/clef-omni":0.1665,"liquid/d1-ultra":0.18528536249391386,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.0022816464348381048,"open/robojev-27b":null,"open/robojev-4b-v2":0.18645454237490924,"open/robojev-4b-v3@0.25":0.02595735713839531,"open/robojev-4b-v3@0.5":0.010566189227213266,"open/robojev-4b-v3@0.75":0.005946149584938689,"open/robojev-4b-v3":0.003138491707937668,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.06623326821562145,"respan/span-02":0.09594737,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.014303972554419531,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0223388671875}},{"suite":"so101","id":"ring_insert/molmoact2/eval_debug_task_cell_1_16h09m_27-jun-2026/ep000002","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000002","predictions":{"RoboJev-27B":0.9951404095689138,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.9,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.6700411694865817,"TypeSafe Jev 1.14":0.84,"Perplexity Decider":0.5736830722769682,"Liquid D1":0.9867771755742815,"Mercury Decide":0.02033235408469743,"Cloudflare Clef":0.8417,"cloudflare/clef-flash":0.8368,"cloudflare/clef-omni":0.435,"liquid/d1-ultra":0.9287049333612218,"open/intern-decision-4b":0.7193152314525416,"open/robojev-27b-v1@0.5":0.8991599039120649,"open/robojev-27b":null,"open/robojev-4b-v2":0.0478308706454966,"open/robojev-4b-v3@0.25":0.9399133324623108,"open/robojev-4b-v3@0.5":0.5328473643492497,"open/robojev-4b-v3@0.75":0.2666072781234324,"open/robojev-4b-v3":0.24208096504423623,"openai/gpt-6-luna-decisions":0.98,"perplexity/pplx-decider-flash-v1.2":0.702721947937954,"respan/span-02":0.08827321,"typesafe/jev-1.13":0.89,"JEV-27B-VL (10 frames)":0.9577113525901041,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.96875}},{"suite":"so101","id":"ring_insert/molmoact2/eval_debug_task_cell_1_16h09m_27-jun-2026/ep000024","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000024","predictions":{"RoboJev-27B":0.004737226175389761,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.009593849407982238,"TypeSafe Jev 1.14":0.07,"Perplexity Decider":0.014483385476497572,"Liquid D1":0.19193278644723683,"Mercury Decide":0.00407013825952249,"Cloudflare Clef":0.2801,"cloudflare/clef-flash":0.3196,"cloudflare/clef-omni":0.1682,"liquid/d1-ultra":0.6551469107189953,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.00051372699546533,"open/robojev-27b":null,"open/robojev-4b-v2":0.011895327908303815,"open/robojev-4b-v3@0.25":0.01243165135383606,"open/robojev-4b-v3@0.5":0.0037133326112963453,"open/robojev-4b-v3@0.75":0.0019267347489025771,"open/robojev-4b-v3":0.0013178502752796797,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.05999206108803907,"respan/span-02":0.15996721,"typesafe/jev-1.13":0.2,"JEV-27B-VL (10 frames)":0.0026062366332639734,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0279541015625}},{"suite":"so101","id":"ring_insert/molmoact2/eval_debug_task_cell_1_16h09m_27-jun-2026/ep000029","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000029","predictions":{"RoboJev-27B":0.017752554272387006,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.04293251726824757,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.032404769935986455,"Liquid D1":0.5,"Mercury Decide":0.008577485382032443,"Cloudflare Clef":0.3531,"cloudflare/clef-flash":0.394,"cloudflare/clef-omni":0.1366,"liquid/d1-ultra":0.718681172204642,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.002254478297933738,"open/robojev-27b":null,"open/robojev-4b-v2":0.10500058508962046,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.009900079472737449,"open/robojev-4b-v3@0.75":0.005946149584938689,"open/robojev-4b-v3":0.003897642342744068,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.212946099945543,"respan/span-02":0.07159221,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.0645847339405837,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.078125}},{"suite":"so101","id":"ring_insert/molmoact2/eval_ring_insert_15h18m_08-jul-2026/ep000000","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000000","predictions":{"RoboJev-27B":0.00413611641480909,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.004913024788782973,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.015946613512562314,"Liquid D1":0.039638843638982,"Mercury Decide":0.0009110510689396431,"Cloudflare Clef":0.118,"cloudflare/clef-flash":0.1651,"cloudflare/clef-omni":0.0742,"liquid/d1-ultra":0.04269763782076913,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.001966251991174891,"open/robojev-27b":null,"open/robojev-4b-v2":0.02400120929134279,"open/robojev-4b-v3@0.25":0.020332353189587593,"open/robojev-4b-v3@0.5":0.008141294289513608,"open/robojev-4b-v3@0.75":0.004692235822472068,"open/robojev-4b-v3":0.002972967407392003,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.06566888134335398,"respan/span-02":0.052829098,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.0017787948179982748,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.07373046875}},{"suite":"so101","id":"ring_insert/molmoact2/eval_ring_insert_15h18m_08-jul-2026/ep000005","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000005","predictions":{"RoboJev-27B":0.006796642823373265,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":0.10732548541839315,"TypeSafe Jev 1.14":0.14,"Perplexity Decider":0.062195339655068176,"Liquid D1":0.3208213138121609,"Mercury Decide":0.015906389116869566,"Cloudflare Clef":0.3149,"cloudflare/clef-flash":0.4079,"cloudflare/clef-omni":0.1748,"liquid/d1-ultra":0.21695809190875665,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.013107616616004144,"open/robojev-27b":null,"open/robojev-4b-v2":0.0790476748344352,"open/robojev-4b-v3@0.25":0.10669060051441193,"open/robojev-4b-v3@0.5":0.04078132817181798,"open/robojev-4b-v3@0.75":0.0171641516746209,"open/robojev-4b-v3":0.012102416042214261,"openai/gpt-6-luna-decisions":0.12,"perplexity/pplx-decider-flash-v1.2":0.17847660593859033,"respan/span-02":0.09090164,"typesafe/jev-1.13":0.34,"JEV-27B-VL (10 frames)":0.006101727639110856,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.03564453125}},{"suite":"so101","id":"ring_insert/molmoact2/eval_ring_insert_15h18m_08-jul-2026/ep000008","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000008","predictions":{"RoboJev-27B":0.9949523043780116,"GPT-6 Astra":0.999,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.96,"Claude Sonnet 5.5":0.92,"JEV-27B-VL":0.8701426511480571,"TypeSafe Jev 1.14":0.47,"Perplexity Decider":0.6618957717182103,"Liquid D1":0.9867771798517426,"Mercury Decide":0.20181323186177208,"Cloudflare Clef":0.8356,"cloudflare/clef-flash":0.7824,"cloudflare/clef-omni":0.3859,"liquid/d1-ultra":0.9781418567838754,"open/intern-decision-4b":0.8998738837161642,"open/robojev-27b-v1@0.5":0.9888013250075528,"open/robojev-27b":null,"open/robojev-4b-v2":0.054313267386278195,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.9507586388020023,"open/robojev-4b-v3@0.75":0.8489244915244398,"open/robojev-4b-v3":0.8126605503046089,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.9047087606764811,"respan/span-02":0.62456954,"typesafe/jev-1.13":0.85,"JEV-27B-VL (10 frames)":0.9481969987040334,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.8671875}},{"suite":"so101","id":"ring_insert/molmoact2/eval_ring_insert_15h18m_08-jul-2026/ep000014","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000014","predictions":{"RoboJev-27B":0.0039029899469990004,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0011067974275314088,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.012596431890859995,"Liquid D1":0.063714997807704,"Mercury Decide":0.002323162742807195,"Cloudflare Clef":0.2512,"cloudflare/clef-flash":0.1132,"cloudflare/clef-omni":0.0474,"liquid/d1-ultra":0.022938862110241716,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.00010604498014322686,"open/robojev-27b":null,"open/robojev-4b-v2":0.004905405551811006,"open/robojev-4b-v3@0.25":0.005911068990826607,"open/robojev-4b-v3@0.5":0.002197092076271529,"open/robojev-4b-v3@0.75":0.0015191329853098835,"open/robojev-4b-v3":0.0009514973249264055,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.02749542838014185,"respan/span-02":0.031123865,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.010468455983919125,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.027587890625}},{"suite":"so101","id":"ring_insert/molmoact2/eval_ring_insert_15h18m_08-jul-2026/ep000021","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000021","predictions":{"RoboJev-27B":0.989296582978343,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.749037207192824,"TypeSafe Jev 1.14":0.76,"Perplexity Decider":0.30381530531643475,"Liquid D1":0.8354835411997897,"Mercury Decide":0.025957354937269386,"Cloudflare Clef":0.5314,"cloudflare/clef-flash":0.6139,"cloudflare/clef-omni":0.1694,"liquid/d1-ultra":0.8727197268349427,"open/intern-decision-4b":0.6932998143038492,"open/robojev-27b-v1@0.5":0.9446500181224387,"open/robojev-27b":null,"open/robojev-4b-v2":0.21506799585334685,"open/robojev-4b-v3@0.25":0.9149009585380554,"open/robojev-4b-v3@0.5":0.9090947575586418,"open/robojev-4b-v3@0.75":0.6843443841953539,"open/robojev-4b-v3":0.3929848669324905,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.5628571055000242,"respan/span-02":0.917391,"typesafe/jev-1.13":0.6,"JEV-27B-VL (10 frames)":0.8875069308052481,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.90234375}},{"suite":"so101","id":"ring_insert/pi0.5/eval_debug_task_cell_1_09h24m_30-jun-2026/ep000006","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000006","predictions":{"RoboJev-27B":0.013470015086163986,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.11810235963138167,"TypeSafe Jev 1.14":0.2,"Perplexity Decider":0.06103920901920595,"Liquid D1":0.4378234991142019,"Mercury Decide":0.05340332735168128,"Cloudflare Clef":0.2921,"cloudflare/clef-flash":0.4237,"cloudflare/clef-omni":0.0915,"liquid/d1-ultra":0.6551469213552649,"open/intern-decision-4b":0.39193998888916504,"open/robojev-27b-v1@0.5":0.029506540362776976,"open/robojev-27b":null,"open/robojev-4b-v2":0.14917689162532846,"open/robojev-4b-v3@0.25":0.562176525592804,"open/robojev-4b-v3@0.5":0.6877183043672045,"open/robojev-4b-v3@0.75":0.302940708044421,"open/robojev-4b-v3":0.1637708093883215,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.43955563096221606,"respan/span-02":0.112198785,"typesafe/jev-1.13":0.27,"JEV-27B-VL (10 frames)":0.013261062335857509,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2041015625}},{"suite":"so101","id":"ring_insert/pi0.5/eval_debug_task_cell_1_09h40m_30-jun-2026/ep000000","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000000","predictions":{"RoboJev-27B":0.9900280680770308,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.7741902119505405,"TypeSafe Jev 1.14":0.69,"Perplexity Decider":0.32213070778908426,"Liquid D1":0.9465966739665496,"Mercury Decide":0.9399133494052115,"Cloudflare Clef":0.4361,"cloudflare/clef-flash":0.5835,"cloudflare/clef-omni":0.1589,"liquid/d1-ultra":0.8727197438305133,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.9561261966914436,"open/robojev-27b":null,"open/robojev-4b-v2":0.26370774468711267,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.9475856495128058,"open/robojev-4b-v3@0.75":0.9282107321543306,"open/robojev-4b-v3":0.828649621504827,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.3842408736332409,"respan/span-02":0.05719243,"typesafe/jev-1.13":0.77,"JEV-27B-VL (10 frames)":0.9374459166854959,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.9609375}},{"suite":"so101","id":"ring_insert/pi0.5/eval_debug_task_cell_1_09h40m_30-jun-2026/ep000001","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000001","predictions":{"RoboJev-27B":0.9899105552172492,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.6279698438585501,"TypeSafe Jev 1.14":0.77,"Perplexity Decider":0.16973866191275466,"Liquid D1":0.9755769095908488,"Mercury Decide":0.05340333224796729,"Cloudflare Clef":0.4031,"cloudflare/clef-flash":0.6197,"cloudflare/clef-omni":0.1623,"liquid/d1-ultra":0.8147146268461545,"open/intern-decision-4b":0.36247442200877295,"open/robojev-27b-v1@0.5":0.9553659220665662,"open/robojev-27b":null,"open/robojev-4b-v2":0.07585818098994364,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.10858632498619036,"open/robojev-4b-v3@0.75":0.1050005837572588,"open/robojev-4b-v3":0.08810813794451551,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.08214577081766082,"respan/span-02":0.8890605,"typesafe/jev-1.13":0.56,"JEV-27B-VL (10 frames)":0.8223350532030462,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.9375}},{"suite":"so101","id":"ring_insert/pi0.5/eval_debug_task_cell_1_09h40m_30-jun-2026/ep000002","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000002","predictions":{"RoboJev-27B":0.9856077084421868,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.7519218414808843,"TypeSafe Jev 1.14":0.69,"Perplexity Decider":0.08571510863208318,"Liquid D1":0.9579122699817195,"Mercury Decide":0.4073334000459302,"Cloudflare Clef":0.4167,"cloudflare/clef-flash":0.5173,"cloudflare/clef-omni":0.2331,"liquid/d1-ultra":0.855341985101059,"open/intern-decision-4b":0.5930110454411601,"open/robojev-27b-v1@0.5":0.9755397426634143,"open/robojev-27b":null,"open/robojev-4b-v2":0.3902102358701789,"open/robojev-4b-v3@0.25":0.9465966820716858,"open/robojev-4b-v3@0.5":0.8914136750138096,"open/robojev-4b-v3@0.75":0.8769960242027004,"open/robojev-4b-v3":0.828649621504827,"openai/gpt-6-luna-decisions":0.99,"perplexity/pplx-decider-flash-v1.2":0.504096177965941,"respan/span-02":0.26565096,"typesafe/jev-1.13":0.67,"JEV-27B-VL (10 frames)":0.7487708264488047,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.9375}},{"suite":"so101","id":"ring_insert/pi0.5/eval_debug_task_cell_1_09h40m_30-jun-2026/ep000011","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000011","predictions":{"RoboJev-27B":0.06084051469812775,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.07947125509083774,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.047228123532445196,"Liquid D1":0.4378234991142019,"Mercury Decide":0.006692851252433582,"Cloudflare Clef":0.3894,"cloudflare/clef-flash":0.4992,"cloudflare/clef-omni":0.2541,"liquid/d1-ultra":0.24316814011226495,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.004196515864887858,"open/robojev-27b":null,"open/robojev-4b-v2":0.021996220940774924,"open/robojev-4b-v3@0.25":0.07585817575454712,"open/robojev-4b-v3@0.5":0.02450159025746704,"open/robojev-4b-v3@0.75":0.013576917981093352,"open/robojev-4b-v3":0.008304581719395627,"openai/gpt-6-luna-decisions":0.17,"perplexity/pplx-decider-flash-v1.2":0.355049535392485,"respan/span-02":0.14763822,"typesafe/jev-1.13":0.37,"JEV-27B-VL (10 frames)":0.3203693396295679,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.09423828125}},{"suite":"so101","id":"ring_insert/pi0.5/eval_debug_task_cell_1_09h40m_30-jun-2026/ep000012","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000012","predictions":{"RoboJev-27B":0.7399327369455356,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.005661164312914268,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.11811959635383623,"Liquid D1":0.19193278644723683,"Mercury Decide":0.0009697520363555695,"Cloudflare Clef":0.2527,"cloudflare/clef-flash":0.313,"cloudflare/clef-omni":0.0645,"liquid/d1-ultra":0.225461603724292,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.00503921553156764,"open/robojev-27b":null,"open/robojev-4b-v2":0.033953688356658976,"open/robojev-4b-v3@0.25":0.8670357465744019,"open/robojev-4b-v3@0.5":0.8707824477141304,"open/robojev-4b-v3@0.75":0.8769960242027004,"open/robojev-4b-v3":0.8761560328980749,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1075046667807623,"respan/span-02":0.047482863,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.007365479087494782,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.004608154296875}},{"suite":"so101","id":"ring_insert/pi0/eval_debug_task_cell_1_08h29m_30-jun-2026/ep000014","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000014","predictions":{"RoboJev-27B":0.014929053557562714,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.009234748807882645,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.029240706468043318,"Liquid D1":0.14804718675485834,"Mercury Decide":0.002182716193826566,"Cloudflare Clef":0.2317,"cloudflare/clef-flash":0.2976,"cloudflare/clef-omni":0.2434,"liquid/d1-ultra":0.11171744345734799,"open/intern-decision-4b":0.4069889545588398,"open/robojev-27b-v1@0.5":0.0008860164651031169,"open/robojev-27b":null,"open/robojev-4b-v2":0.021056067200550033,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.02154587702420825,"open/robojev-4b-v3@0.75":0.019292242704938834,"open/robojev-4b-v3":0.013473327870331066,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.11629750214352862,"respan/span-02":0.043276314,"typesafe/jev-1.13":0.18,"JEV-27B-VL (10 frames)":0.003807012741104315,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00628662109375}},{"suite":"so101","id":"ring_insert/pi0/eval_debug_task_cell_1_09h09m_30-jun-2026/ep000003","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000003","predictions":{"RoboJev-27B":0.022032869735835917,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.09947418145601812,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.05842650472363027,"Liquid D1":0.2018132174596823,"Mercury Decide":0.01406362376319878,"Cloudflare Clef":0.2379,"cloudflare/clef-flash":0.3856,"cloudflare/clef-omni":0.1608,"liquid/d1-ultra":0.27144692389371533,"open/intern-decision-4b":0.37709365395745764,"open/robojev-27b-v1@0.5":0.01752373472052491,"open/robojev-27b":null,"open/robojev-4b-v2":0.06698650224956176,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.020201721614979237,"open/robojev-4b-v3@0.75":0.011381877728436919,"open/robojev-4b-v3":0.0053922199218183735,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.1253103522568364,"respan/span-02":0.8974256,"typesafe/jev-1.13":0.17,"JEV-27B-VL (10 frames)":0.05965801128419484,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0966796875}},{"suite":"so101","id":"ring_insert/pi0/eval_debug_task_cell_1_09h09m_30-jun-2026/ep000012","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000012","predictions":{"RoboJev-27B":0.013381675528330405,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.023297653501697633,"TypeSafe Jev 1.14":0.13,"Perplexity Decider":0.16431364644288654,"Liquid D1":0.679178699175393,"Mercury Decide":0.005220125176080461,"Cloudflare Clef":0.1337,"cloudflare/clef-flash":0.3794,"cloudflare/clef-omni":0.1625,"liquid/d1-ultra":0.281318827795358,"open/intern-decision-4b":0.34810523633137336,"open/robojev-27b-v1@0.5":0.003035467458831907,"open/robojev-27b":null,"open/robojev-4b-v2":0.08579678054051716,"open/robojev-4b-v3@0.25":0.18242551386356354,"open/robojev-4b-v3@0.5":0.04924136119799765,"open/robojev-4b-v3@0.75":0.05133579603952293,"open/robojev-4b-v3":0.0299371453325719,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3084078477498777,"respan/span-02":0.63309383,"typesafe/jev-1.13":0.37,"JEV-27B-VL (10 frames)":0.005332705879954955,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.328125}},{"suite":"so101","id":"ring_insert/smolvla/eval_debug_task_cell_1_10h35m_24-jun-2026/ep000005","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000005","predictions":{"RoboJev-27B":0.010865357597666348,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.0468948478651186,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.05659559826203216,"Liquid D1":0.40733341443526055,"Mercury Decide":0.022977371039038345,"Cloudflare Clef":0.2095,"cloudflare/clef-flash":0.3368,"cloudflare/clef-omni":0.1685,"liquid/d1-ultra":0.6092789268213934,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.011541286430729053,"open/robojev-27b":null,"open/robojev-4b-v2":0.3588504266804245,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.03828411009766295,"open/robojev-4b-v3@0.75":0.020451257661610673,"open/robojev-4b-v3":0.009760866998496955,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1736709467473502,"respan/span-02":0.13123237,"typesafe/jev-1.13":0.32,"JEV-27B-VL (10 frames)":0.005369685133130276,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0140380859375}},{"suite":"so101","id":"ring_insert/smolvla/eval_debug_task_cell_1_10h35m_24-jun-2026/ep000006","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000006","predictions":{"RoboJev-27B":0.014923594568010061,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.08529153157419593,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.11697401255168621,"Liquid D1":0.16451646699291617,"Mercury Decide":0.01798621414031,"Cloudflare Clef":0.2303,"cloudflare/clef-flash":0.3175,"cloudflare/clef-omni":0.0998,"liquid/d1-ultra":0.21695808391083074,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.01422252232197539,"open/robojev-27b":null,"open/robojev-4b-v2":0.10087862681469857,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.022977370307335907,"open/robojev-4b-v3@0.75":0.011381877728436919,"open/robojev-4b-v3":0.005691671058411752,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.09759988860865978,"respan/span-02":0.3364765,"typesafe/jev-1.13":0.17,"JEV-27B-VL (10 frames)":0.06463886587773628,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.25390625}},{"suite":"so101","id":"ring_insert/smolvla/eval_debug_task_cell_1_10h35m_24-jun-2026/ep000011","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000011","predictions":{"RoboJev-27B":0.014624880040676443,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.015434395780262185,"TypeSafe Jev 1.14":0.11,"Perplexity Decider":0.02451185457374423,"Liquid D1":0.29421497216298875,"Mercury Decide":0.005911069315939758,"Cloudflare Clef":0.286,"cloudflare/clef-flash":0.38,"cloudflare/clef-omni":0.1407,"liquid/d1-ultra":0.6209651888367838,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.0010347857038611478,"open/robojev-27b":null,"open/robojev-4b-v2":0.02400120929134279,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.009275566578748366,"open/robojev-4b-v3@0.75":0.0034885936902831075,"open/robojev-4b-v3":0.0019267345803236512,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.21958499910451268,"respan/span-02":0.122719385,"typesafe/jev-1.13":0.31,"JEV-27B-VL (10 frames)":0.02403886094286288,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.04150390625}},{"suite":"so101","id":"ring_insert/smolvla/eval_debug_task_cell_1_10h35m_24-jun-2026/ep000016","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000016","predictions":{"RoboJev-27B":0.9944916286344063,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":0.797503749809488,"TypeSafe Jev 1.14":0.55,"Perplexity Decider":0.4450576995159173,"Liquid D1":0.9953904277095224,"Mercury Decide":0.04742587351415913,"Cloudflare Clef":0.6181,"cloudflare/clef-flash":0.9083,"cloudflare/clef-omni":0.2792,"liquid/d1-ultra":0.8426924853912474,"open/intern-decision-4b":0.7064759712765732,"open/robojev-27b-v1@0.5":0.9490668246632477,"open/robojev-27b":null,"open/robojev-4b-v2":0.0790476748344352,"open/robojev-4b-v3@0.25":0.970687747001648,"open/robojev-4b-v3@0.5":0.9822447263824892,"open/robojev-4b-v3@0.75":0.9693020651146849,"open/robojev-4b-v3":0.9495393243071166,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.856319367426793,"respan/span-02":0.41976672,"typesafe/jev-1.13":0.87,"JEV-27B-VL (10 frames)":0.8656212734381337,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.953125}},{"suite":"so101","id":"ring_insert/smolvla/eval_debug_task_cell_1_10h35m_24-jun-2026/ep000027","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000027","predictions":{"RoboJev-27B":0.9946660620735865,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.8888820687686355,"TypeSafe Jev 1.14":0.85,"Perplexity Decider":0.49176886540341974,"Liquid D1":0.9964063977320488,"Mercury Decide":0.0953494738965146,"Cloudflare Clef":0.6129,"cloudflare/clef-flash":0.8907,"cloudflare/clef-omni":0.8023,"liquid/d1-ultra":0.9407227437444688,"open/intern-decision-4b":0.9053865123447689,"open/robojev-27b-v1@0.5":0.9653195862072869,"open/robojev-27b":null,"open/robojev-4b-v2":0.04990557889898353,"open/robojev-4b-v3@0.25":0.851952850818634,"open/robojev-4b-v3@0.5":0.21151967170194583,"open/robojev-4b-v3@0.75":0.13643297762397494,"open/robojev-4b-v3":0.09724120311457327,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.7403106103162153,"respan/span-02":0.37999988,"typesafe/jev-1.13":0.69,"JEV-27B-VL (10 frames)":0.9630483032201438,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.96484375}},{"suite":"so101","id":"ring_insert/smolvla/eval_debug_task_cell_1_10h35m_24-jun-2026/ep000028","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000028","predictions":{"RoboJev-27B":0.9952897037498665,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.96,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":0.7660089705596956,"TypeSafe Jev 1.14":0.84,"Perplexity Decider":0.7731547351549874,"Liquid D1":0.990291524879525,"Mercury Decide":0.03308598029553404,"Cloudflare Clef":0.767,"cloudflare/clef-flash":0.8491,"cloudflare/clef-omni":0.7528,"liquid/d1-ultra":0.9844287332551139,"open/intern-decision-4b":0.8184242551251981,"open/robojev-27b-v1@0.5":0.9711758695586341,"open/robojev-27b":null,"open/robojev-4b-v2":0.16086775395337108,"open/robojev-4b-v3@0.25":0.970687747001648,"open/robojev-4b-v3@0.5":0.9328665051276483,"open/robojev-4b-v3@0.75":0.7668262163944938,"open/robojev-4b-v3":0.527147193867567,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.9025866290274766,"respan/span-02":0.93421334,"typesafe/jev-1.13":0.89,"JEV-27B-VL (10 frames)":0.9744679038902604,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.93359375}},{"suite":"so101","id":"ring_insert/smolvla/eval_debug_task_cell_1_11h01m_24-jun-2026/ep000002","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000002","predictions":{"RoboJev-27B":0.995502070539851,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":0.7795307094673872,"TypeSafe Jev 1.14":0.86,"Perplexity Decider":0.1992590728583335,"Liquid D1":0.9840936060722768,"Mercury Decide":0.05340332810495602,"Cloudflare Clef":0.7278,"cloudflare/clef-flash":0.8638,"cloudflare/clef-omni":0.5416,"liquid/d1-ultra":0.9791727521112229,"open/intern-decision-4b":0.8940776460411956,"open/robojev-27b-v1@0.5":0.9864204960224255,"open/robojev-27b":null,"open/robojev-4b-v2":0.2003788035719567,"open/robojev-4b-v3@0.25":0.957912266254425,"open/robojev-4b-v3@0.5":0.5974224658882353,"open/robojev-4b-v3@0.75":0.22270014231977903,"open/robojev-4b-v3":0.11806640532074496,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.9111927505023988,"respan/span-02":0.87191755,"typesafe/jev-1.13":0.7,"JEV-27B-VL (10 frames)":0.9421507906979693,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.9453125}},{"suite":"so101","id":"ring_insert/smolvla/eval_debug_task_cell_1_11h01m_24-jun-2026/ep000008","task":"Insert the colourful ring into the central wooden peg","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000008","predictions":{"RoboJev-27B":0.0023049635080056165,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0015200978071461216,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.009804394770488811,"Liquid D1":0.03514484640079327,"Mercury Decide":0.001098730966621178,"Cloudflare Clef":0.197,"cloudflare/clef-flash":0.1727,"cloudflare/clef-omni":0.0653,"liquid/d1-ultra":0.049177954343773214,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.00019572156452213262,"open/robojev-27b":null,"open/robojev-4b-v2":0.006692850868879798,"open/robojev-4b-v3@0.25":0.009708477184176445,"open/robojev-4b-v3@0.5":0.002675199388665972,"open/robojev-4b-v3@0.75":0.0017108587429636138,"open/robojev-4b-v3":0.0016373401530355304,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.08219694572325949,"respan/span-02":0.067558706,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.001967835111915061,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01324462890625}},{"suite":"so101","id":"ring_insert/smolvla/eval_debug_task_cell_1_11h01m_24-jun-2026/ep000009","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"ring_insert","episode":"ep000009","predictions":{"RoboJev-27B":0.9955460517360055,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.96,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":0.8333468168766098,"TypeSafe Jev 1.14":0.72,"Perplexity Decider":0.8580031446487378,"Liquid D1":0.9840936067720373,"Mercury Decide":0.11920291419948606,"Cloudflare Clef":0.8634,"cloudflare/clef-flash":0.7032,"cloudflare/clef-omni":0.1214,"liquid/d1-ultra":0.948461735802091,"open/intern-decision-4b":0.788764540067536,"open/robojev-27b-v1@0.5":0.9849381089864193,"open/robojev-27b":null,"open/robojev-4b-v2":0.06983116708754197,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.9703110587107732,"open/robojev-4b-v3@0.75":0.93575028740662,"open/robojev-4b-v3":0.9278650639695798,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.9511585056345637,"respan/span-02":0.91274184,"typesafe/jev-1.13":0.92,"JEV-27B-VL (10 frames)":0.9702021625753952,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.94140625}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000001","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000001","predictions":{"RoboJev-27B":0.896063764519713,"GPT-6 Astra":0.77,"GPT-6.1 Sol":0.78,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.5536494440780738,"TypeSafe Jev 1.14":0.46,"Perplexity Decider":0.3723612098685194,"Liquid D1":0.7549149813536518,"Mercury Decide":0.651354857898194,"Cloudflare Clef":0.2922,"cloudflare/clef-flash":0.478,"cloudflare/clef-omni":0.3531,"liquid/d1-ultra":0.6770986984253415,"open/intern-decision-4b":0.37709365395745764,"open/robojev-27b-v1@0.5":0.6067559786304163,"open/robojev-27b":null,"open/robojev-4b-v2":0.001842766452331557,"open/robojev-4b-v3@0.25":0.7772998809814453,"open/robojev-4b-v3@0.5":0.7657040237782665,"open/robojev-4b-v3@0.75":0.32865255101542173,"open/robojev-4b-v3":0.24208096504423623,"openai/gpt-6-luna-decisions":0.49,"perplexity/pplx-decider-flash-v1.2":0.5039304877306549,"respan/span-02":0.8415794,"typesafe/jev-1.13":0.49,"JEV-27B-VL (10 frames)":0.6242561224808837,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1083984375}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000002","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000002","predictions":{"RoboJev-27B":0.7512842330088142,"GPT-6 Astra":0.64,"GPT-6.1 Sol":0.8,"Claude Opus 5.5":0.45,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.5536494440780738,"TypeSafe Jev 1.14":0.49,"Perplexity Decider":0.36940793530933586,"Liquid D1":0.5926665999540697,"Mercury Decide":0.5621765008857981,"Cloudflare Clef":0.3963,"cloudflare/clef-flash":0.5047,"cloudflare/clef-omni":0.2195,"liquid/d1-ultra":0.6325127183904117,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.5115532721612024,"open/robojev-27b":null,"open/robojev-4b-v2":0.0023025598229782147,"open/robojev-4b-v3@0.25":0.6791787147521973,"open/robojev-4b-v3@0.5":0.741279894904784,"open/robojev-4b-v3@0.75":0.302940708044421,"open/robojev-4b-v3":0.21343419258585974,"openai/gpt-6-luna-decisions":0.14,"perplexity/pplx-decider-flash-v1.2":0.5244320209101849,"respan/span-02":0.844753,"typesafe/jev-1.13":0.63,"JEV-27B-VL (10 frames)":0.3840194831118242,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1318359375}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000004","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000004","predictions":{"RoboJev-27B":0.00908611304919565,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.03730578886635678,"TypeSafe Jev 1.14":0.07,"Perplexity Decider":0.037869295500651,"Liquid D1":0.37754066879814546,"Mercury Decide":0.008577485350352902,"Cloudflare Clef":0.2559,"cloudflare/clef-flash":0.2454,"cloudflare/clef-omni":0.0927,"liquid/d1-ultra":0.059277259208907446,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.0030547028460428836,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016121527751335812,"open/robojev-4b-v3@0.25":0.01798621006309986,"open/robojev-4b-v3@0.5":0.0051522412018618095,"open/robojev-4b-v3@0.75":0.0029197498822566025,"open/robojev-4b-v3":0.0022671624120110317,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.11626104686864336,"respan/span-02":0.12240023,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.06522037784309165,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.007568359375}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000006","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000006","predictions":{"RoboJev-27B":0.004939874886013217,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.046723025721917916,"TypeSafe Jev 1.14":0.16,"Perplexity Decider":0.023261829525817533,"Liquid D1":0.24508501313237172,"Mercury Decide":0.006692850305136358,"Cloudflare Clef":0.3382,"cloudflare/clef-flash":0.3278,"cloudflare/clef-omni":0.0962,"liquid/d1-ultra":0.07463357051825908,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.0017867527082031512,"open/robojev-27b":null,"open/robojev-4b-v2":0.001233791749980779,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.007626874902958847,"open/robojev-4b-v3@0.75":0.00204466165068541,"open/robojev-4b-v3":0.0013178502752796797,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.20141839471020953,"respan/span-02":0.13808249,"typesafe/jev-1.13":0.21,"JEV-27B-VL (10 frames)":0.009029672519091628,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0078125}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000009","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000009","predictions":{"RoboJev-27B":0.0038029207085091563,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0033096221247789245,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.01678118576401642,"Liquid D1":0.08509904732734556,"Mercury Decide":0.0013250223013686771,"Cloudflare Clef":0.1848,"cloudflare/clef-flash":0.2494,"cloudflare/clef-omni":0.0741,"liquid/d1-ultra":0.04917795007868597,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":0.0010485798136661637,"open/robojev-27b":null,"open/robojev-4b-v2":0.0012900470555811355,"open/robojev-4b-v3@0.25":0.02595735713839531,"open/robojev-4b-v3@0.5":0.0037133326112963453,"open/robojev-4b-v3@0.75":0.0014314726301544898,"open/robojev-4b-v3":0.001004586699177363,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.0605387457688498,"respan/span-02":0.1115637,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.0029932072910939687,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01031494140625}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000011","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000011","predictions":{"RoboJev-27B":0.9911030830226595,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.5838657458401092,"TypeSafe Jev 1.14":0.56,"Perplexity Decider":0.8168039974920074,"Liquid D1":0.0850990438468576,"Mercury Decide":0.9626731143960903,"Cloudflare Clef":0.167,"cloudflare/clef-flash":0.3844,"cloudflare/clef-omni":0.0776,"liquid/d1-ultra":0.13286532447020155,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.9590989389894437,"open/robojev-27b":null,"open/robojev-4b-v2":0.0014746525778226533,"open/robojev-4b-v3@0.25":0.5926666259765625,"open/robojev-4b-v3@0.5":0.9368711827232762,"open/robojev-4b-v3@0.75":0.978321636049121,"open/robojev-4b-v3":0.9823937644522028,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.27782453374023736,"respan/span-02":0.11078117,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.5344742560848322,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.007568359375}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000012","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000012","predictions":{"RoboJev-27B":0.9711576394406174,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.86,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.6966947089388685,"TypeSafe Jev 1.14":0.59,"Perplexity Decider":0.6234601622291651,"Liquid D1":0.8175744806385543,"Mercury Decide":0.9465966668104392,"Cloudflare Clef":0.3039,"cloudflare/clef-flash":0.3845,"cloudflare/clef-omni":0.0741,"liquid/d1-ultra":0.620965177756194,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.9599517855189093,"open/robojev-27b":null,"open/robojev-4b-v2":0.0022022489536237186,"open/robojev-4b-v3@0.25":0.8933094143867493,"open/robojev-4b-v3@0.5":0.9442201868171092,"open/robojev-4b-v3@0.75":0.9613683489514899,"open/robojev-4b-v3":0.9610789635262862,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.30643562582545447,"respan/span-02":0.1969574,"typesafe/jev-1.13":0.68,"JEV-27B-VL (10 frames)":0.5439978125666216,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006500244140625}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000013","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000013","predictions":{"RoboJev-27B":0.012789469621613267,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.08,"JEV-27B-VL":0.10513171601080307,"TypeSafe Jev 1.14":0.26,"Perplexity Decider":0.08795535719993267,"Liquid D1":0.5312093733737563,"Mercury Decide":0.02931222788947056,"Cloudflare Clef":0.2368,"cloudflare/clef-flash":0.4228,"cloudflare/clef-omni":0.1342,"liquid/d1-ultra":0.3122040868290014,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.015789031182612785,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016121527751335812,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.01664357488299338,"open/robojev-4b-v3@0.75":0.006308531582070822,"open/robojev-4b-v3":0.004343237452522156,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1391002137058005,"respan/span-02":0.16395567,"typesafe/jev-1.13":0.26,"JEV-27B-VL (10 frames)":0.0762811185433536,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01495361328125}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000014","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000014","predictions":{"RoboJev-27B":0.006263003506017556,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0523375839254853,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.026339548548561503,"Liquid D1":0.2120688093369431,"Mercury Decide":0.025957355219835308,"Cloudflare Clef":0.2151,"cloudflare/clef-flash":0.2944,"cloudflare/clef-omni":0.066,"liquid/d1-ultra":0.10691173965049809,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.0033477896154934274,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016121527751335812,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.006269376036423619,"open/robojev-4b-v3@0.75":0.0021697908424400778,"open/robojev-4b-v3":0.0015508634943190564,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.10408421712290965,"respan/span-02":0.13178046,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.026266508085048566,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00421142578125}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000015","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000015","predictions":{"RoboJev-27B":0.01640387660763529,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.12980401565776298,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.11655453828432706,"Liquid D1":0.32082130082460697,"Mercury Decide":0.0259573547488921,"Cloudflare Clef":0.3026,"cloudflare/clef-flash":0.4197,"cloudflare/clef-omni":0.1079,"liquid/d1-ultra":0.11671092643799169,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.02861424232302039,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016121527751335812,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.012842048097105568,"open/robojev-4b-v3@0.75":0.004978582695254881,"open/robojev-4b-v3":0.0023934843568307186,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.25974311327641203,"respan/span-02":0.09637607,"typesafe/jev-1.13":0.12,"JEV-27B-VL (10 frames)":0.155547893436931,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00860595703125}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000016","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000016","predictions":{"RoboJev-27B":0.989858886723989,"GPT-6 Astra":0.92,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.5950487531329015,"TypeSafe Jev 1.14":0.61,"Perplexity Decider":0.5313563767708938,"Liquid D1":0.7772998663336157,"Mercury Decide":0.7981867849406659,"Cloudflare Clef":0.317,"cloudflare/clef-flash":0.3693,"cloudflare/clef-omni":0.1189,"liquid/d1-ultra":0.549204909864935,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.9077376649751082,"open/robojev-27b":null,"open/robojev-4b-v2":0.009125637690971435,"open/robojev-4b-v3@0.25":0.8354835510253906,"open/robojev-4b-v3@0.5":0.9537489247538957,"open/robojev-4b-v3@0.75":0.9795487423383894,"open/robojev-4b-v3":0.9814286862202798,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.36068649918097745,"respan/span-02":0.13528518,"typesafe/jev-1.13":0.57,"JEV-27B-VL (10 frames)":0.5065839559221235,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0169677734375}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000017","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000017","predictions":{"RoboJev-27B":0.9863924567303883,"GPT-6 Astra":0.9,"GPT-6.1 Sol":0.86,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.39559345375651545,"TypeSafe Jev 1.14":0.41,"Perplexity Decider":0.382827662120091,"Liquid D1":0.2942149845400438,"Mercury Decide":0.7057850216484838,"Cloudflare Clef":0.3138,"cloudflare/clef-flash":0.3838,"cloudflare/clef-omni":0.1097,"liquid/d1-ultra":0.40253406552936266,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.824728761951904,"open/robojev-27b":null,"open/robojev-4b-v2":0.002876746893908692,"open/robojev-4b-v3@0.25":0.5926666259765625,"open/robojev-4b-v3@0.5":0.9241418233387945,"open/robojev-4b-v3@0.75":0.9726532127177251,"open/robojev-4b-v3":0.9814286862202798,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.39397528474082094,"respan/span-02":0.16307181,"typesafe/jev-1.13":0.29,"JEV-27B-VL (10 frames)":0.45037888079843796,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00592041015625}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000019","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000019","predictions":{"RoboJev-27B":0.9762743349542339,"GPT-6 Astra":0.92,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.5153406814864652,"TypeSafe Jev 1.14":0.5,"Perplexity Decider":0.5418210548261245,"Liquid D1":0.3775406828054583,"Mercury Decide":0.8807970779778823,"Cloudflare Clef":0.2831,"cloudflare/clef-flash":0.3522,"cloudflare/clef-omni":0.1003,"liquid/d1-ultra":0.5,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.8888403281403842,"open/robojev-27b":null,"open/robojev-4b-v2":0.002751490629587489,"open/robojev-4b-v3@0.25":0.8354835510253906,"open/robojev-4b-v3@0.5":0.9507586388020023,"open/robojev-4b-v3@0.75":0.9726532127177251,"open/robojev-4b-v3":0.9757703987213749,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.3130160379081653,"respan/span-02":0.3013825,"typesafe/jev-1.13":0.58,"JEV-27B-VL (10 frames)":0.4044737657538552,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0078125}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000020","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000020","predictions":{"RoboJev-27B":0.980048736599787,"GPT-6 Astra":0.86,"GPT-6.1 Sol":0.85,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.425404961571833,"TypeSafe Jev 1.14":0.53,"Perplexity Decider":0.4071382953514314,"Liquid D1":0.37754066879814546,"Mercury Decide":0.34864513533394575,"Cloudflare Clef":0.2712,"cloudflare/clef-flash":0.3483,"cloudflare/clef-omni":0.1074,"liquid/d1-ultra":0.5974659344706373,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.40007193112170303,"open/robojev-27b":null,"open/robojev-4b-v2":0.004488287139460313,"open/robojev-4b-v3@0.25":0.6513549089431763,"open/robojev-4b-v3@0.5":0.9565659184411002,"open/robojev-4b-v3@0.75":0.9710246026727085,"open/robojev-4b-v3":0.9730632228114633,"openai/gpt-6-luna-decisions":0.11,"perplexity/pplx-decider-flash-v1.2":0.3695838988974419,"respan/span-02":0.1263588,"typesafe/jev-1.13":0.4,"JEV-27B-VL (10 frames)":0.293824509242673,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.005218505859375}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000021","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000021","predictions":{"RoboJev-27B":0.013597178030646563,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.02120454208438248,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.024000953704927573,"Liquid D1":0.05340333431947304,"Mercury Decide":0.004609572260565194,"Cloudflare Clef":0.1291,"cloudflare/clef-flash":0.2615,"cloudflare/clef-omni":0.0733,"liquid/d1-ultra":0.03531702148293739,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.003268568011239535,"open/robojev-27b":null,"open/robojev-4b-v2":0.0017624512139676404,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.003964844872971652,"open/robojev-4b-v3@0.75":0.0023025600819802016,"open/robojev-4b-v3":0.0013913520410630778,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.08074435199894305,"respan/span-02":0.10580907,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.03150939056113807,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00360107421875}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000024","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000024","predictions":{"RoboJev-27B":0.03349497539892302,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.29834604757917593,"TypeSafe Jev 1.14":0.22,"Perplexity Decider":0.13988653567342213,"Liquid D1":0.5312093733737563,"Mercury Decide":0.2942149845400438,"Cloudflare Clef":0.3213,"cloudflare/clef-flash":0.4473,"cloudflare/clef-omni":0.2319,"liquid/d1-ultra":0.1708421934681112,"open/intern-decision-4b":0.4069889545588398,"open/robojev-27b-v1@0.5":0.021327222598795763,"open/robojev-27b":null,"open/robojev-4b-v2":0.001410358480093293,"open/robojev-4b-v3@0.25":0.2689414322376251,"open/robojev-4b-v3@0.5":0.0671334948723516,"open/robojev-4b-v3@0.75":0.0171641516746209,"open/robojev-4b-v3":0.0074556149068047885,"openai/gpt-6-luna-decisions":0.17,"perplexity/pplx-decider-flash-v1.2":0.3571579630341696,"respan/span-02":0.2999109,"typesafe/jev-1.13":0.37,"JEV-27B-VL (10 frames)":0.13390189193687896,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.046630859375}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000026","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000026","predictions":{"RoboJev-27B":0.004779944864642019,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.00795712737335787,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.01715774590856522,"Liquid D1":0.11279540180929934,"Mercury Decide":0.0015978457555061636,"Cloudflare Clef":0.113,"cloudflare/clef-flash":0.2506,"cloudflare/clef-omni":0.0717,"liquid/d1-ultra":0.04476157374131474,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.0010324545530525555,"open/robojev-27b":null,"open/robojev-4b-v2":0.001410358480093293,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.007626874902958847,"open/robojev-4b-v3@0.75":0.0021697908424400778,"open/robojev-4b-v3":0.0015508634943190564,"openai/gpt-6-luna-decisions":0.1,"perplexity/pplx-decider-flash-v1.2":0.08249103424733766,"respan/span-02":0.22501999,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.006664391337111115,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0113525390625}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000027","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000027","predictions":{"RoboJev-27B":0.9446593669090859,"GPT-6 Astra":0.8,"GPT-6.1 Sol":0.79,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.5345460039801715,"TypeSafe Jev 1.14":0.42,"Perplexity Decider":0.37765049241308335,"Liquid D1":0.7310585727705126,"Mercury Decide":0.5,"Cloudflare Clef":0.6016,"cloudflare/clef-flash":0.5313,"cloudflare/clef-omni":0.3009,"liquid/d1-ultra":0.6877959081164229,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.6806133968170213,"open/robojev-27b":null,"open/robojev-4b-v2":0.154932285758515,"open/robojev-4b-v3@0.25":0.3486451506614685,"open/robojev-4b-v3@0.5":0.386860966015097,"open/robojev-4b-v3@0.75":0.36918510345682914,"open/robojev-4b-v3":0.3303678724294036,"openai/gpt-6-luna-decisions":0.15,"perplexity/pplx-decider-flash-v1.2":0.4228353237697463,"respan/span-02":0.48816368,"typesafe/jev-1.13":0.48,"JEV-27B-VL (10 frames)":0.5289535082392633,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.103515625}},{"suite":"so101","id":"tool_insert/diffusion/eval_debug_task_cell_1_08h49m_25-jun-2026/ep000029","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000029","predictions":{"RoboJev-27B":0.0030659328164920133,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0036150412293059677,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.017960296245016664,"Liquid D1":0.02297736823741426,"Mercury Decide":0.0013250223555937534,"Cloudflare Clef":0.0774,"cloudflare/clef-flash":0.1402,"cloudflare/clef-omni":0.0583,"liquid/d1-ultra":0.029173330217155964,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.0004545861797585005,"open/robojev-27b":null,"open/robojev-4b-v2":0.001926734644431273,"open/robojev-4b-v3@0.25":0.009708477184176445,"open/robojev-4b-v3@0.5":0.0032570072049156237,"open/robojev-4b-v3@0.75":0.0018155968873527504,"open/robojev-4b-v3":0.001004586699177363,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.022639738147279376,"respan/span-02":0.04697716,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.003092072653961509,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00537109375}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000000","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000000","predictions":{"RoboJev-27B":0.6373698905827696,"GPT-6 Astra":0.9,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.35,"JEV-27B-VL":0.03943680543596002,"TypeSafe Jev 1.14":0.19,"Perplexity Decider":0.04886812789366518,"Liquid D1":0.1329642436335826,"Mercury Decide":0.025957357762928745,"Cloudflare Clef":0.2447,"cloudflare/clef-flash":0.2666,"cloudflare/clef-omni":0.0814,"liquid/d1-ultra":0.0978441741944513,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.5809614950799281,"open/robojev-27b":null,"open/robojev-4b-v2":0.001926734644431273,"open/robojev-4b-v3@0.25":0.22270014882087708,"open/robojev-4b-v3@0.5":0.8195287241994405,"open/robojev-4b-v3@0.75":0.8704295270205443,"open/robojev-4b-v3":0.7478081785025862,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.19822130183831926,"respan/span-02":0.15279607,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.0429427335838532,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0174560546875}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000001","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000001","predictions":{"RoboJev-27B":0.9850395005235938,"GPT-6 Astra":0.18,"GPT-6.1 Sol":0.89,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.68,"JEV-27B-VL":0.13511396586121902,"TypeSafe Jev 1.14":0.37,"Perplexity Decider":0.28830730052393966,"Liquid D1":0.08035746551861317,"Mercury Decide":0.020332352192498855,"Cloudflare Clef":0.223,"cloudflare/clef-flash":0.2203,"cloudflare/clef-omni":0.1076,"liquid/d1-ultra":0.3790348222438061,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.9235664629881276,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016856305131264125,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.897619749088608,"open/robojev-4b-v3@0.75":0.9590959433649857,"open/robojev-4b-v3":0.952080652301484,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.2062218057793881,"respan/span-02":0.13833784,"typesafe/jev-1.13":0.22,"JEV-27B-VL (10 frames)":0.2701733606972333,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00537109375}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000002","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000002","predictions":{"RoboJev-27B":0.985453022400548,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.6422481720748642,"TypeSafe Jev 1.14":0.64,"Perplexity Decider":0.8168556504270191,"Liquid D1":0.4073334000459302,"Mercury Decide":0.952574129515172,"Cloudflare Clef":0.3267,"cloudflare/clef-flash":0.3787,"cloudflare/clef-omni":0.0898,"liquid/d1-ultra":0.774538396275708,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.9579129749684916,"open/robojev-27b":null,"open/robojev-4b-v2":0.0020145213081092066,"open/robojev-4b-v3@0.25":0.4687906503677368,"open/robojev-4b-v3@0.5":0.8707824477141304,"open/robojev-4b-v3@0.75":0.9320774407500154,"open/robojev-4b-v3":0.9468707387904532,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.3259338015025056,"respan/span-02":0.09158565,"typesafe/jev-1.13":0.64,"JEV-27B-VL (10 frames)":0.44370500807710883,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0028076171875}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000003","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000003","predictions":{"RoboJev-27B":0.9841670940378907,"GPT-6 Astra":0.92,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.5076426485640868,"TypeSafe Jev 1.14":0.57,"Perplexity Decider":0.3704756906027098,"Liquid D1":0.5926665999540697,"Mercury Decide":0.7772998560157665,"Cloudflare Clef":0.4152,"cloudflare/clef-flash":0.3864,"cloudflare/clef-omni":0.0968,"liquid/d1-ultra":0.21695809190875665,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.855370240406736,"open/robojev-27b":null,"open/robojev-4b-v2":0.001926734644431273,"open/robojev-4b-v3@0.25":0.8354835510253906,"open/robojev-4b-v3@0.5":0.9241418233387945,"open/robojev-4b-v3@0.75":0.9320774407500154,"open/robojev-4b-v3":0.9161618129189448,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.47559556968412814,"respan/span-02":0.14361835,"typesafe/jev-1.13":0.56,"JEV-27B-VL (10 frames)":0.4823297629310711,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.003082275390625}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000004","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000004","predictions":{"RoboJev-27B":0.9787865594107235,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.5612498578091117,"TypeSafe Jev 1.14":0.43,"Perplexity Decider":0.5804482014728513,"Liquid D1":0.3208212878370535,"Mercury Decide":0.8519527982093668,"Cloudflare Clef":0.2816,"cloudflare/clef-flash":0.3688,"cloudflare/clef-omni":0.109,"liquid/d1-ultra":0.4753376834348995,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.9210990843820186,"open/robojev-27b":null,"open/robojev-4b-v2":0.12300397797247992,"open/robojev-4b-v3@0.25":0.622459352016449,"open/robojev-4b-v3@0.5":0.9507586388020023,"open/robojev-4b-v3@0.75":0.9818023083761724,"open/robojev-4b-v3":0.9833095447847391,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.4967086790556727,"respan/span-02":0.11226378,"typesafe/jev-1.13":0.53,"JEV-27B-VL (10 frames)":0.36941416143271344,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.010009765625}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000005","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000005","predictions":{"RoboJev-27B":0.004793225540082654,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.00276848234633333,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.016958348795403387,"Liquid D1":0.24508501313237172,"Mercury Decide":0.001325022236052111,"Cloudflare Clef":0.1969,"cloudflare/clef-flash":0.2499,"cloudflare/clef-omni":0.088,"liquid/d1-ultra":0.04269764263148309,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.0022042680828068604,"open/robojev-27b":null,"open/robojev-4b-v2":0.001348863876427256,"open/robojev-4b-v3@0.25":0.03308597952127457,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.0016121526329810115,"open/robojev-4b-v3":0.00106063530615271,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.05028652636249246,"respan/span-02":0.16072115,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.014231431986079937,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0093994140625}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000008","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000008","predictions":{"RoboJev-27B":0.11105982003308283,"GPT-6 Astra":0.83,"GPT-6.1 Sol":0.87,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.22304632738466526,"TypeSafe Jev 1.14":0.17,"Perplexity Decider":0.11175606004469127,"Liquid D1":0.1259227681153614,"Mercury Decide":0.11920292045759123,"Cloudflare Clef":0.2487,"cloudflare/clef-flash":0.2265,"cloudflare/clef-omni":0.0681,"liquid/d1-ultra":0.12728027316505724,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.32664321923093226,"open/robojev-27b":null,"open/robojev-4b-v2":0.004106490957182719,"open/robojev-4b-v3@0.25":0.13296423852443695,"open/robojev-4b-v3@0.5":0.2847434534005251,"open/robojev-4b-v3@0.75":0.6843443841953539,"open/robojev-4b-v3":0.3303678724294036,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.21075171200545964,"respan/span-02":0.12286361,"typesafe/jev-1.13":0.21,"JEV-27B-VL (10 frames)":0.059013669250640416,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006500244140625}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000009","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000009","predictions":{"RoboJev-27B":0.9907756560244487,"GPT-6 Astra":0.93,"GPT-6.1 Sol":0.92,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.1938550270197048,"TypeSafe Jev 1.14":0.63,"Perplexity Decider":0.32804175066303926,"Liquid D1":0.10669059394565118,"Mercury Decide":0.22270014398423357,"Cloudflare Clef":0.1858,"cloudflare/clef-flash":0.2938,"cloudflare/clef-omni":0.0967,"liquid/d1-ultra":0.5974659231483984,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.9585376052912791,"open/robojev-27b":null,"open/robojev-4b-v2":0.002106299096066607,"open/robojev-4b-v3@0.25":0.7772998809814453,"open/robojev-4b-v3@0.5":0.972148766331303,"open/robojev-4b-v3@0.75":0.9847328451036568,"open/robojev-4b-v3":0.9823937644522028,"openai/gpt-6-luna-decisions":0.06,"perplexity/pplx-decider-flash-v1.2":0.3586234782675212,"respan/span-02":0.10464126,"typesafe/jev-1.13":0.24,"JEV-27B-VL (10 frames)":0.5051094877374616,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00141143798828125}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000013","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000013","predictions":{"RoboJev-27B":0.9584315755405196,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.75,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.35411224581695666,"TypeSafe Jev 1.14":0.49,"Perplexity Decider":0.43868585577828506,"Liquid D1":0.32082130082460697,"Mercury Decide":0.6224593312018546,"Cloudflare Clef":0.3348,"cloudflare/clef-flash":0.3142,"cloudflare/clef-omni":0.0856,"liquid/d1-ultra":0.5974659231483984,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.8000861749975062,"open/robojev-27b":null,"open/robojev-4b-v2":0.0024074285712443492,"open/robojev-4b-v3@0.25":0.43782350420951843,"open/robojev-4b-v3@0.5":0.8780062831580779,"open/robojev-4b-v3@0.75":0.9541617453379198,"open/robojev-4b-v3":0.9700628546674281,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.3312781732126219,"respan/span-02":0.18283923,"typesafe/jev-1.13":0.5,"JEV-27B-VL (10 frames)":0.35275427000248766,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01495361328125}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000014","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000014","predictions":{"RoboJev-27B":0.030281723863664366,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.9,"Claude Opus 5.5":0.62,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.05252892460864923,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.041441374785611974,"Liquid D1":0.0803574721258011,"Mercury Decide":0.037326887879581695,"Cloudflare Clef":0.1825,"cloudflare/clef-flash":0.2717,"cloudflare/clef-omni":0.0702,"liquid/d1-ultra":0.0565836624356303,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.01857574636740265,"open/robojev-27b":null,"open/robojev-4b-v2":0.0015418730931173695,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.013703364243695216,"open/robojev-4b-v3@0.75":0.015267154896343218,"open/robojev-4b-v3":0.01421514020851167,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.11479370433289902,"respan/span-02":0.14285153,"typesafe/jev-1.13":0.12,"JEV-27B-VL (10 frames)":0.040647059755890856,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0185546875}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000015","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000015","predictions":{"RoboJev-27B":0.008854533724963075,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0596564514973722,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.03240100247389389,"Liquid D1":0.3775406828054583,"Mercury Decide":0.03308597767364294,"Cloudflare Clef":0.3042,"cloudflare/clef-flash":0.3484,"cloudflare/clef-omni":0.087,"liquid/d1-ultra":0.062090635771172846,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.005316621275385457,"open/robojev-27b":null,"open/robojev-4b-v2":0.0015418730931173695,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.009900079472737449,"open/robojev-4b-v3@0.75":0.003927901618504033,"open/robojev-4b-v3":0.0022671624120110317,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.12762374205893118,"respan/span-02":0.14244239,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.02862123105263425,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.015869140625}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000017","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000017","predictions":{"RoboJev-27B":0.9825565853166734,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.42728873950400936,"TypeSafe Jev 1.14":0.53,"Perplexity Decider":0.34774636195644676,"Liquid D1":0.2018132174596823,"Mercury Decide":0.2018132174596823,"Cloudflare Clef":0.2661,"cloudflare/clef-flash":0.3712,"cloudflare/clef-omni":0.1007,"liquid/d1-ultra":0.6092789156141315,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.917296435502591,"open/robojev-27b":null,"open/robojev-4b-v2":0.003007688028932422,"open/robojev-4b-v3@0.25":0.3775406777858734,"open/robojev-4b-v3@0.5":0.9565659184411002,"open/robojev-4b-v3@0.75":0.9807077572950611,"open/robojev-4b-v3":0.9841784582307415,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.3945469517768317,"respan/span-02":0.17637466,"typesafe/jev-1.13":0.46,"JEV-27B-VL (10 frames)":0.361812606883846,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01324462890625}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000020","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000020","predictions":{"RoboJev-27B":0.8480749125551661,"GPT-6 Astra":0.73,"GPT-6.1 Sol":0.78,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.35411224581695666,"TypeSafe Jev 1.14":0.3,"Perplexity Decider":0.2550670415542569,"Liquid D1":0.679178699175393,"Mercury Decide":0.18242552602881168,"Cloudflare Clef":0.3185,"cloudflare/clef-flash":0.4498,"cloudflare/clef-omni":0.2058,"liquid/d1-ultra":0.4753376834348995,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.2051798171961911,"open/robojev-27b":null,"open/robojev-4b-v2":0.2003788035719567,"open/robojev-4b-v3@0.25":0.3208213150501251,"open/robojev-4b-v3@0.5":0.32658221149990796,"open/robojev-4b-v3@0.75":0.27840626377504696,"open/robojev-4b-v3":0.2625786543234272,"openai/gpt-6-luna-decisions":0.11,"perplexity/pplx-decider-flash-v1.2":0.48213765544280596,"respan/span-02":0.8032559,"typesafe/jev-1.13":0.37,"JEV-27B-VL (10 frames)":0.5316560032434134,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.07470703125}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000021","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000021","predictions":{"RoboJev-27B":0.9858179131525395,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.3247669287800877,"TypeSafe Jev 1.14":0.36,"Perplexity Decider":0.35290000496729146,"Liquid D1":0.23370635691404026,"Mercury Decide":0.2018132150593341,"Cloudflare Clef":0.2616,"cloudflare/clef-flash":0.3321,"cloudflare/clef-omni":0.0897,"liquid/d1-ultra":0.20868888924130843,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.8389660843620632,"open/robojev-27b":null,"open/robojev-4b-v2":0.001926734644431273,"open/robojev-4b-v3@0.25":0.29421496391296387,"open/robojev-4b-v3@0.5":0.9328665051276483,"open/robojev-4b-v3@0.75":0.9770226303212622,"open/robojev-4b-v3":0.9770226297071284,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2838153128291856,"respan/span-02":0.69252056,"typesafe/jev-1.13":0.34,"JEV-27B-VL (10 frames)":0.23054134334711154,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0128173828125}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000022","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000022","predictions":{"RoboJev-27B":0.974229158760582,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.5631456222291983,"TypeSafe Jev 1.14":0.46,"Perplexity Decider":0.5352917769969462,"Liquid D1":0.32082130082460697,"Mercury Decide":0.5312093733737563,"Cloudflare Clef":0.2684,"cloudflare/clef-flash":0.4232,"cloudflare/clef-omni":0.1168,"liquid/d1-ultra":0.3790348222438061,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.9304919502333313,"open/robojev-27b":null,"open/robojev-4b-v2":0.0024074285712443492,"open/robojev-4b-v3@0.25":0.7549149990081787,"open/robojev-4b-v3@0.5":0.9592186718281821,"open/robojev-4b-v3@0.75":0.9807077572950611,"open/robojev-4b-v3":0.9841784582307415,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.35230035489736083,"respan/span-02":0.16703255,"typesafe/jev-1.13":0.35,"JEV-27B-VL (10 frames)":0.5231951118200199,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.012451171875}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000024","task":"Insert the missing tool into the empty slot on the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000024","predictions":{"RoboJev-27B":0.05925599881477914,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.89,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.65,"JEV-27B-VL":0.12467267714545574,"TypeSafe Jev 1.14":0.45,"Perplexity Decider":0.10176413956716036,"Liquid D1":0.3775406547908327,"Mercury Decide":0.13296423504419938,"Cloudflare Clef":0.2295,"cloudflare/clef-flash":0.2507,"cloudflare/clef-omni":0.0766,"liquid/d1-ultra":0.1446580090739025,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.16790193221301192,"open/robojev-27b":null,"open/robojev-4b-v2":0.001348863876427256,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.02612421708095358,"open/robojev-4b-v3@0.75":0.0143976132495814,"open/robojev-4b-v3":0.012102416042214261,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2716905978614078,"respan/span-02":0.14971009,"typesafe/jev-1.13":0.38,"JEV-27B-VL (10 frames)":0.09945685000467219,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.004058837890625}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000025","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000025","predictions":{"RoboJev-27B":0.9871280071828596,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.7,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.3032055443326022,"TypeSafe Jev 1.14":0.36,"Perplexity Decider":0.27259791026770963,"Liquid D1":0.15610489351941398,"Mercury Decide":0.16451646904109268,"Cloudflare Clef":0.2533,"cloudflare/clef-flash":0.3178,"cloudflare/clef-omni":0.1356,"liquid/d1-ultra":0.4876613324012321,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.7624841052572173,"open/robojev-27b":null,"open/robojev-4b-v2":0.03863165331656982,"open/robojev-4b-v3@0.25":0.18242551386356354,"open/robojev-4b-v3@0.5":0.5654124215707017,"open/robojev-4b-v3@0.75":0.948664203960477,"open/robojev-4b-v3":0.9610789635262862,"openai/gpt-6-luna-decisions":0.06,"perplexity/pplx-decider-flash-v1.2":0.3053029664772467,"respan/span-02":0.21802808,"typesafe/jev-1.13":0.23,"JEV-27B-VL (10 frames)":0.17898271288382245,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00360107421875}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000026","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000026","predictions":{"RoboJev-27B":0.9842707175240557,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.65,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.5422027347558217,"TypeSafe Jev 1.14":0.61,"Perplexity Decider":0.6581837806298796,"Liquid D1":0.6513548646660542,"Mercury Decide":0.9399133498259924,"Cloudflare Clef":0.2597,"cloudflare/clef-flash":0.2916,"cloudflare/clef-omni":0.095,"liquid/d1-ultra":0.6551469000827254,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.9265706509064024,"open/robojev-27b":null,"open/robojev-4b-v2":0.003007688028932422,"open/robojev-4b-v3@0.25":0.622459352016449,"open/robojev-4b-v3@0.5":0.961715889902337,"open/robojev-4b-v3@0.75":0.9741927167604716,"open/robojev-4b-v3":0.9793403302916414,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.3482426369756921,"respan/span-02":0.1494271,"typesafe/jev-1.13":0.35,"JEV-27B-VL (10 frames)":0.470432641942713,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00421142578125}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000027","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000027","predictions":{"RoboJev-27B":0.9835377304210317,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.24370604299752693,"TypeSafe Jev 1.14":0.58,"Perplexity Decider":0.21246180005247706,"Liquid D1":0.14804718675485834,"Mercury Decide":0.1329642384799526,"Cloudflare Clef":0.2662,"cloudflare/clef-flash":0.3728,"cloudflare/clef-omni":0.0706,"liquid/d1-ultra":0.4507950668241079,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":0.4177470146500394,"open/robojev-27b":null,"open/robojev-4b-v2":0.0017624512139676404,"open/robojev-4b-v3@0.25":0.13296423852443695,"open/robojev-4b-v3@0.5":0.386860966015097,"open/robojev-4b-v3@0.75":0.8892726892788834,"open/robojev-4b-v3":0.8874762480971222,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.2892477719404422,"respan/span-02":0.18828258,"typesafe/jev-1.13":0.22,"JEV-27B-VL (10 frames)":0.3483224451492779,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00628662109375}},{"suite":"so101","id":"tool_insert/pi0/eval_debug_task_cell_1_14h26m_29-jun-2026/ep000029","task":"Insert the missing tool into the empty slot on the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_insert","episode":"ep000029","predictions":{"RoboJev-27B":0.9607240056589579,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.21644369147816483,"TypeSafe Jev 1.14":0.47,"Perplexity Decider":0.2113114258602203,"Liquid D1":0.08035747322699913,"Mercury Decide":0.06008665354025422,"Cloudflare Clef":0.2142,"cloudflare/clef-flash":0.283,"cloudflare/clef-omni":0.0722,"liquid/d1-ultra":0.27144691923857645,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.5882378556016924,"open/robojev-27b":null,"open/robojev-4b-v2":0.0022022489536237186,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.1447586588133107,"open/robojev-4b-v3@0.75":0.41165138407414853,"open/robojev-4b-v3":0.632621183102026,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.12482749099886321,"respan/span-02":0.046820883,"typesafe/jev-1.13":0.17,"JEV-27B-VL (10 frames)":0.3754641395184065,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.040283203125}},{"suite":"so101","id":"tool_removal/molmoact2/eval_debug_task_cell_1_12h08m_27-jun-2026/ep000000","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000000","predictions":{"RoboJev-27B":0.011073882437545757,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":0.15214976132223385,"TypeSafe Jev 1.14":0.32,"Perplexity Decider":0.035820470208155944,"Liquid D1":0.3073580295544412,"Mercury Decide":0.060086656906500974,"Cloudflare Clef":0.1132,"cloudflare/clef-flash":0.2864,"cloudflare/clef-omni":0.1813,"liquid/d1-ultra":0.11171743644957713,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.07700059777011914,"open/robojev-27b":null,"open/robojev-4b-v2":0.012991835391526811,"open/robojev-4b-v3@0.25":0.10669060051441193,"open/robojev-4b-v3@0.5":0.153095448827493,"open/robojev-4b-v3@0.75":0.08013780136639623,"open/robojev-4b-v3":0.053129261209546814,"openai/gpt-6-luna-decisions":0.17,"perplexity/pplx-decider-flash-v1.2":0.26323320415464896,"respan/span-02":0.08981428,"typesafe/jev-1.13":0.34,"JEV-27B-VL (10 frames)":0.07504923654256926,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.008056640625}},{"suite":"so101","id":"tool_removal/molmoact2/eval_debug_task_cell_1_12h08m_27-jun-2026/ep000001","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000001","predictions":{"RoboJev-27B":0.9890931946366922,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.68,"JEV-27B-VL":0.8354752198356973,"TypeSafe Jev 1.14":0.61,"Perplexity Decider":0.7369788865880442,"Liquid D1":0.9770226292536686,"Mercury Decide":0.9706877678706987,"Cloudflare Clef":0.7229,"cloudflare/clef-flash":0.4915,"cloudflare/clef-omni":0.7693,"liquid/d1-ultra":0.8071467802341742,"open/intern-decision-4b":0.8748864949022742,"open/robojev-27b-v1@0.5":0.9411682784459059,"open/robojev-27b":null,"open/robojev-4b-v2":0.9926866549449824,"open/robojev-4b-v3@0.25":0.9840936064720154,"open/robojev-4b-v3@0.5":0.9928552745771213,"open/robojev-4b-v3@0.75":0.9924673890431385,"open/robojev-4b-v3":0.9916954182806045,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.8301974890642048,"respan/span-02":0.8157071,"typesafe/jev-1.13":0.69,"JEV-27B-VL (10 frames)":0.7758309122902711,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.8515625}},{"suite":"so101","id":"tool_removal/molmoact2/eval_debug_task_cell_1_12h08m_27-jun-2026/ep000003","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000003","predictions":{"RoboJev-27B":0.01584484951099674,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.23528944636627316,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.05742492179791401,"Liquid D1":0.1645164628965632,"Mercury Decide":0.2018132150593341,"Cloudflare Clef":0.2428,"cloudflare/clef-flash":0.322,"cloudflare/clef-omni":0.1752,"liquid/d1-ultra":0.10691174302179943,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.09178319948093577,"open/robojev-27b":null,"open/robojev-4b-v2":0.013576916891431232,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.12199371684192196,"open/robojev-4b-v3@0.75":0.1295704729794557,"open/robojev-4b-v3":0.10211768392406631,"openai/gpt-6-luna-decisions":0.1,"perplexity/pplx-decider-flash-v1.2":0.24277969471021962,"respan/span-02":0.057587095,"typesafe/jev-1.13":0.18,"JEV-27B-VL (10 frames)":0.13282459097202695,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0032806396484375}},{"suite":"so101","id":"tool_removal/molmoact2/eval_debug_task_cell_1_12h08m_27-jun-2026/ep000005","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000005","predictions":{"RoboJev-27B":0.9888745791815355,"GPT-6 Astra":0.9,"GPT-6.1 Sol":0.1,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.8365312260233088,"TypeSafe Jev 1.14":0.59,"Perplexity Decider":0.7297626492442871,"Liquid D1":0.9553191322715435,"Mercury Decide":0.984093609162886,"Cloudflare Clef":0.5859,"cloudflare/clef-flash":0.642,"cloudflare/clef-omni":0.7196,"liquid/d1-ultra":0.8220509968168928,"open/intern-decision-4b":0.8089141677995819,"open/robojev-27b-v1@0.5":0.9379161524927033,"open/robojev-27b":null,"open/robojev-4b-v2":0.9875683488625845,"open/robojev-4b-v3@0.25":0.9890130758285522,"open/robojev-4b-v3@0.5":0.9944993245326874,"open/robojev-4b-v3@0.75":0.9933071492776461,"open/robojev-4b-v3":0.9925443850931952,"openai/gpt-6-luna-decisions":0.91,"perplexity/pplx-decider-flash-v1.2":0.650477238022986,"respan/span-02":0.8750642,"typesafe/jev-1.13":0.77,"JEV-27B-VL (10 frames)":0.7329416210828651,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.5703125}},{"suite":"so101","id":"tool_removal/molmoact2/eval_debug_task_cell_1_12h08m_27-jun-2026/ep000009","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000009","predictions":{"RoboJev-27B":0.9895594252284242,"GPT-6 Astra":0.1,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.795004646319641,"TypeSafe Jev 1.14":0.73,"Perplexity Decider":0.7303614322279309,"Liquid D1":0.9724147195719217,"Mercury Decide":0.9770226279992099,"Cloudflare Clef":0.4078,"cloudflare/clef-flash":0.4913,"cloudflare/clef-omni":0.6305,"liquid/d1-ultra":0.8553419909260974,"open/intern-decision-4b":0.4069889545588398,"open/robojev-27b-v1@0.5":0.9478543361377955,"open/robojev-27b":null,"open/robojev-4b-v2":0.9900305883062807,"open/robojev-4b-v3@0.25":0.9820137619972229,"open/robojev-4b-v3@0.5":0.9918587057104864,"open/robojev-4b-v3@0.75":0.9915231617842919,"open/robojev-4b-v3":0.9891305427743544,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.7449599571408009,"respan/span-02":0.77399534,"typesafe/jev-1.13":0.75,"JEV-27B-VL (10 frames)":0.6619790479009755,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.6875}},{"suite":"so101","id":"tool_removal/molmoact2/eval_debug_task_cell_1_12h08m_27-jun-2026/ep000011","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000011","predictions":{"RoboJev-27B":0.21272272160546046,"GPT-6 Astra":0.82,"GPT-6.1 Sol":0.78,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.13783699691096188,"TypeSafe Jev 1.14":0.14,"Perplexity Decider":0.08336852185459427,"Liquid D1":0.3775406828054583,"Mercury Decide":0.05340332735168128,"Cloudflare Clef":0.2878,"cloudflare/clef-flash":0.443,"cloudflare/clef-omni":0.2663,"liquid/d1-ultra":0.31220408177442577,"open/intern-decision-4b":0.36247442200877295,"open/robojev-27b-v1@0.5":0.025960340130731018,"open/robojev-27b":null,"open/robojev-4b-v2":0.011895327908303815,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.07585817666120565,"open/robojev-4b-v3@0.75":0.02580728323952834,"open/robojev-4b-v3":0.012102416042214261,"openai/gpt-6-luna-decisions":0.06,"perplexity/pplx-decider-flash-v1.2":0.18752889309549892,"respan/span-02":0.18417726,"typesafe/jev-1.13":0.25,"JEV-27B-VL (10 frames)":0.6666496313569195,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.03173828125}},{"suite":"so101","id":"tool_removal/molmoact2/eval_debug_task_cell_1_12h08m_27-jun-2026/ep000012","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000012","predictions":{"RoboJev-27B":0.9889641848826327,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.92,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.760441599465787,"TypeSafe Jev 1.14":0.41,"Perplexity Decider":0.7427261623189491,"Liquid D1":0.9399133468805266,"Mercury Decide":0.9579122677288678,"Cloudflare Clef":0.367,"cloudflare/clef-flash":0.5042,"cloudflare/clef-omni":0.6629,"liquid/d1-ultra":0.822051010590282,"open/intern-decision-4b":0.7318060856600669,"open/robojev-27b-v1@0.5":0.9573043442584158,"open/robojev-27b":null,"open/robojev-4b-v2":0.9815345221267577,"open/robojev-4b-v3@0.25":0.9840936064720154,"open/robojev-4b-v3@0.5":0.9907244334212516,"open/robojev-4b-v3@0.75":0.9892687880395139,"open/robojev-4b-v3":0.9850028225488837,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.5617276430093346,"respan/span-02":0.25018966,"typesafe/jev-1.13":0.57,"JEV-27B-VL (10 frames)":0.6933659939502027,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.546875}},{"suite":"so101","id":"tool_removal/molmoact2/eval_debug_task_cell_1_12h08m_27-jun-2026/ep000016","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000016","predictions":{"RoboJev-27B":0.9870266795781425,"GPT-6 Astra":0.1,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.68,"JEV-27B-VL":0.8212457286007666,"TypeSafe Jev 1.14":0.59,"Perplexity Decider":0.6710134624451005,"Liquid D1":0.9465966762263737,"Mercury Decide":0.9840936086963789,"Cloudflare Clef":0.6257,"cloudflare/clef-flash":0.4917,"cloudflare/clef-omni":0.6225,"liquid/d1-ultra":0.8426924822708843,"open/intern-decision-4b":0.608060011110835,"open/robojev-27b-v1@0.5":0.9550527550041505,"open/robojev-27b":null,"open/robojev-4b-v2":0.9830850866395109,"open/robojev-4b-v3@0.25":0.9840936064720154,"open/robojev-4b-v3@0.5":0.9907244334212516,"open/robojev-4b-v3@0.75":0.9892687880395139,"open/robojev-4b-v3":0.9823937644522028,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.7237440406772079,"respan/span-02":0.5911013,"typesafe/jev-1.13":0.68,"JEV-27B-VL (10 frames)":0.7561751571529566,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.6640625}},{"suite":"so101","id":"tool_removal/molmoact2/eval_debug_task_cell_1_12h08m_27-jun-2026/ep000017","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000017","predictions":{"RoboJev-27B":0.015307121365650277,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.06,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":0.07296713554583568,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.036861804779216106,"Liquid D1":0.3208213138121609,"Mercury Decide":0.025957358233872005,"Cloudflare Clef":0.2859,"cloudflare/clef-flash":0.3669,"cloudflare/clef-omni":0.2378,"liquid/d1-ultra":0.23419873846123568,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.0142311166283138,"open/robojev-27b":null,"open/robojev-4b-v2":0.1381957315129781,"open/robojev-4b-v3@0.25":0.3775406777858734,"open/robojev-4b-v3@0.5":0.22270012535630726,"open/robojev-4b-v3@0.75":0.1295704729794557,"open/robojev-4b-v3":0.05887058738679302,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.19725713613045143,"respan/span-02":0.37059236,"typesafe/jev-1.13":0.2,"JEV-27B-VL (10 frames)":0.2663456600518257,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0284423828125}},{"suite":"so101","id":"tool_removal/molmoact2/eval_debug_task_cell_1_12h08m_27-jun-2026/ep000021","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000021","predictions":{"RoboJev-27B":0.00914283613305587,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.11890693743351921,"TypeSafe Jev 1.14":0.11,"Perplexity Decider":0.03098036748862854,"Liquid D1":0.2018132270610754,"Mercury Decide":0.0373268852023206,"Cloudflare Clef":0.2267,"cloudflare/clef-flash":0.2669,"cloudflare/clef-omni":0.1781,"liquid/d1-ultra":0.12728027316505724,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.022816315944733167,"open/robojev-27b":null,"open/robojev-4b-v2":0.009125637690971435,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.03593407330933149,"open/robojev-4b-v3@0.75":0.02167836395087896,"open/robojev-4b-v3":0.012769726034700673,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.14015485130995023,"respan/span-02":0.10985751,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.09922326242790395,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.010009765625}},{"suite":"so101","id":"tool_removal/molmoact2/eval_debug_task_cell_1_12h08m_27-jun-2026/ep000023","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000023","predictions":{"RoboJev-27B":0.009978789820418063,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.1173024821565874,"TypeSafe Jev 1.14":0.18,"Perplexity Decider":0.046180454066411594,"Liquid D1":0.23370636225126956,"Mercury Decide":0.06008665311947337,"Cloudflare Clef":0.1398,"cloudflare/clef-flash":0.3299,"cloudflare/clef-omni":0.1782,"liquid/d1-ultra":0.17084220347133822,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.03641743594577648,"open/robojev-27b":null,"open/robojev-4b-v2":0.01549249627965257,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.04625107524610428,"open/robojev-4b-v3@0.75":0.02297736967873775,"open/robojev-4b-v3":0.012102416042214261,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.21334564298724365,"respan/span-02":0.18538976,"typesafe/jev-1.13":0.15,"JEV-27B-VL (10 frames)":0.19499423179652503,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.036865234375}},{"suite":"so101","id":"tool_removal/molmoact2/eval_debug_task_cell_1_12h08m_27-jun-2026/ep000026","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000026","predictions":{"RoboJev-27B":0.9890042358803961,"GPT-6 Astra":0.93,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.803651798417099,"TypeSafe Jev 1.14":0.35,"Perplexity Decider":0.7044507071090059,"Liquid D1":0.9669140233989487,"Mercury Decide":0.9859363700641142,"Cloudflare Clef":0.5413,"cloudflare/clef-flash":0.5005,"cloudflare/clef-omni":0.7569,"liquid/d1-ultra":0.8832890772019308,"open/intern-decision-4b":0.6518947636686268,"open/robojev-27b-v1@0.5":0.9266571856390516,"open/robojev-27b":null,"open/robojev-4b-v2":0.9886181217784766,"open/robojev-4b-v3@0.25":0.9820137619972229,"open/robojev-4b-v3@0.5":0.9907244334212516,"open/robojev-4b-v3@0.75":0.9904617124585662,"open/robojev-4b-v3":0.9885304277460041,"openai/gpt-6-luna-decisions":0.93,"perplexity/pplx-decider-flash-v1.2":0.5210156530725136,"respan/span-02":0.62691236,"typesafe/jev-1.13":0.71,"JEV-27B-VL (10 frames)":0.7336734238042765,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.72265625}},{"suite":"so101","id":"tool_removal/molmoact2/eval_debug_task_cell_1_12h08m_27-jun-2026/ep000028","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000028","predictions":{"RoboJev-27B":0.011297047498376046,"GPT-6 Astra":0.15,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.18790752028515795,"TypeSafe Jev 1.14":0.23,"Perplexity Decider":0.04500792715150026,"Liquid D1":0.5621765008857981,"Mercury Decide":0.0675466845698721,"Cloudflare Clef":0.2158,"cloudflare/clef-flash":0.3198,"cloudflare/clef-omni":0.2193,"liquid/d1-ultra":0.2813188230362935,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.05279400724573281,"open/robojev-27b":null,"open/robojev-4b-v2":0.03700737584165394,"open/robojev-4b-v3@0.25":0.10669060051441193,"open/robojev-4b-v3@0.5":0.03828411009766295,"open/robojev-4b-v3@0.75":0.020451257661610673,"open/robojev-4b-v3":0.010869457225645628,"openai/gpt-6-luna-decisions":0.06,"perplexity/pplx-decider-flash-v1.2":0.13946521005290505,"respan/span-02":0.13951312,"typesafe/jev-1.13":0.42,"JEV-27B-VL (10 frames)":0.16047275862509205,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.008056640625}},{"suite":"so101","id":"tool_removal/pi0.5/eval_debug_task_cell_1_07h52m_30-jun-2026/ep000000","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000000","predictions":{"RoboJev-27B":0.07466561158517204,"GPT-6 Astra":0.92,"GPT-6.1 Sol":0.91,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.16340422870127636,"TypeSafe Jev 1.14":0.19,"Perplexity Decider":0.08225574455536767,"Liquid D1":0.3208213138121609,"Mercury Decide":0.042087729267329864,"Cloudflare Clef":0.2285,"cloudflare/clef-flash":0.4101,"cloudflare/clef-omni":0.3035,"liquid/d1-ultra":0.414461257641393,"open/intern-decision-4b":0.36247442200877295,"open/robojev-27b-v1@0.5":0.08916147704248041,"open/robojev-27b":null,"open/robojev-4b-v2":0.013576916891431232,"open/robojev-4b-v3@0.25":0.29421496391296387,"open/robojev-4b-v3@0.5":0.1447586588133107,"open/robojev-4b-v3@0.75":0.054313266183183405,"open/robojev-4b-v3":0.02297737029287157,"openai/gpt-6-luna-decisions":0.11,"perplexity/pplx-decider-flash-v1.2":0.1971309212076664,"respan/span-02":0.740912,"typesafe/jev-1.13":0.34,"JEV-27B-VL (10 frames)":0.3030420350656378,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.03564453125}},{"suite":"so101","id":"tool_removal/pi0.5/eval_debug_task_cell_1_07h52m_30-jun-2026/ep000001","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000001","predictions":{"RoboJev-27B":0.9883112464691594,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.740250404732747,"TypeSafe Jev 1.14":0.59,"Perplexity Decider":0.5593828960190438,"Liquid D1":0.9465966653038896,"Mercury Decide":0.9770226275392417,"Cloudflare Clef":0.4762,"cloudflare/clef-flash":0.6305,"cloudflare/clef-omni":0.4333,"liquid/d1-ultra":0.8291578031974798,"open/intern-decision-4b":0.6932998143038492,"open/robojev-27b-v1@0.5":0.9542621790477487,"open/robojev-27b":null,"open/robojev-4b-v2":0.9908743623090286,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.9923731250970411,"open/robojev-4b-v3@0.75":0.9933071492776461,"open/robojev-4b-v3":0.9916954182806045,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.7796026639022013,"respan/span-02":0.8905228,"typesafe/jev-1.13":0.72,"JEV-27B-VL (10 frames)":0.7705542638886724,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.50390625}},{"suite":"so101","id":"tool_removal/pi0.5/eval_debug_task_cell_1_07h52m_30-jun-2026/ep000004","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000004","predictions":{"RoboJev-27B":0.010025165846729621,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.049909392044902016,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.036327939927326976,"Liquid D1":0.15610489940847916,"Mercury Decide":0.017986212725637506,"Cloudflare Clef":0.1704,"cloudflare/clef-flash":0.2977,"cloudflare/clef-omni":0.1632,"liquid/d1-ultra":0.1446580250927591,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.008713868697963967,"open/robojev-27b":null,"open/robojev-4b-v2":0.011895327908303815,"open/robojev-4b-v3@0.25":0.07585817575454712,"open/robojev-4b-v3@0.5":0.03828411009766295,"open/robojev-4b-v3@0.75":0.02167836395087896,"open/robojev-4b-v3":0.013473327870331066,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.11191349518823555,"respan/span-02":0.1766175,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.0835854613413067,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.02197265625}},{"suite":"so101","id":"tool_removal/pi0.5/eval_debug_task_cell_1_07h52m_30-jun-2026/ep000005","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000005","predictions":{"RoboJev-27B":0.9799397719904199,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.8166780783464538,"TypeSafe Jev 1.14":0.55,"Perplexity Decider":0.690635297951386,"Liquid D1":0.9770226292536686,"Mercury Decide":0.904650527388829,"Cloudflare Clef":0.5215,"cloudflare/clef-flash":0.6484,"cloudflare/clef-omni":0.8884,"liquid/d1-ultra":0.8426924822708843,"open/intern-decision-4b":0.8604937671763584,"open/robojev-27b-v1@0.5":0.9407383293612225,"open/robojev-27b":null,"open/robojev-4b-v2":0.9935974948097437,"open/robojev-4b-v3@0.25":0.9890130758285522,"open/robojev-4b-v3@0.5":0.9937306239635765,"open/robojev-4b-v3@0.75":0.9933071492776461,"open/robojev-4b-v3":0.9921312523406053,"openai/gpt-6-luna-decisions":0.98,"perplexity/pplx-decider-flash-v1.2":0.6134102531835981,"respan/span-02":0.74077475,"typesafe/jev-1.13":0.48,"JEV-27B-VL (10 frames)":0.6551792342724937,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1982421875}},{"suite":"so101","id":"tool_removal/pi0.5/eval_debug_task_cell_1_07h52m_30-jun-2026/ep000014","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000014","predictions":{"RoboJev-27B":0.8495668418487327,"GPT-6 Astra":0.85,"GPT-6.1 Sol":0.86,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.10881029876045933,"TypeSafe Jev 1.14":0.17,"Perplexity Decider":0.0701934443999046,"Liquid D1":0.19193279106941588,"Mercury Decide":0.06008664428307651,"Cloudflare Clef":0.1656,"cloudflare/clef-flash":0.2934,"cloudflare/clef-omni":0.1534,"liquid/d1-ultra":0.2086888659183117,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.051106796628068746,"open/robojev-27b":null,"open/robojev-4b-v2":0.01929224350793923,"open/robojev-4b-v3@0.25":0.29421496391296387,"open/robojev-4b-v3@0.5":0.4184967522309292,"open/robojev-4b-v3@0.75":0.4407557950301173,"open/robojev-4b-v3":0.7772998505135637,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.2249394085969575,"respan/span-02":0.19263752,"typesafe/jev-1.13":0.21,"JEV-27B-VL (10 frames)":0.46230451513256726,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.048828125}},{"suite":"so101","id":"tool_removal/pi0.5/eval_debug_task_cell_1_08h09m_30-jun-2026/ep000001","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000001","predictions":{"RoboJev-27B":0.16152419581429162,"GPT-6 Astra":0.64,"GPT-6.1 Sol":0.18,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.04936438759899297,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.032575721374048065,"Liquid D1":0.2689414213699951,"Mercury Decide":0.02297736991002561,"Cloudflare Clef":0.2152,"cloudflare/clef-flash":0.3278,"cloudflare/clef-omni":0.1901,"liquid/d1-ultra":0.27144691923857645,"open/intern-decision-4b":0.43758935794935333,"open/robojev-27b-v1@0.5":0.005775437822870639,"open/robojev-27b":null,"open/robojev-4b-v2":0.02506949741812164,"open/robojev-4b-v3@0.25":0.2689414322376251,"open/robojev-4b-v3@0.5":0.1368024864039654,"open/robojev-4b-v3@0.75":0.05133579603952293,"open/robojev-4b-v3":0.018571313779720225,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.2413081113417203,"respan/span-02":0.16155057,"typesafe/jev-1.13":0.22,"JEV-27B-VL (10 frames)":0.6162573201899669,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0302734375}},{"suite":"so101","id":"tool_removal/pi0.5/eval_debug_task_cell_1_08h09m_30-jun-2026/ep000004","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000004","predictions":{"RoboJev-27B":0.01310506422943429,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.033495663365815255,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.020702447626036687,"Liquid D1":0.1919327772028789,"Mercury Decide":0.010986941355477658,"Cloudflare Clef":0.1544,"cloudflare/clef-flash":0.2745,"cloudflare/clef-omni":0.1471,"liquid/d1-ultra":0.23419873423953771,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.0035446632787763705,"open/robojev-27b":null,"open/robojev-4b-v2":0.01691491336048918,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.02450159025746704,"open/robojev-4b-v3@0.75":0.012802394334981567,"open/robojev-4b-v3":0.0074556149068047885,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.13465163386960818,"respan/span-02":0.16747195,"typesafe/jev-1.13":0.13,"JEV-27B-VL (10 frames)":0.06369534826039648,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0174560546875}},{"suite":"so101","id":"tool_removal/pi0.5/eval_debug_task_cell_1_08h09m_30-jun-2026/ep000007","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000007","predictions":{"RoboJev-27B":0.9907576870356761,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.9134616520026637,"TypeSafe Jev 1.14":0.69,"Perplexity Decider":0.7705988409834429,"Liquid D1":0.9626731121204184,"Mercury Decide":0.9914225152753181,"Cloudflare Clef":0.5249,"cloudflare/clef-flash":0.4728,"cloudflare/clef-omni":0.7083,"liquid/d1-ultra":0.8781030321845865,"open/intern-decision-4b":0.5930110454411601,"open/robojev-27b-v1@0.5":0.971729507223407,"open/robojev-27b":null,"open/robojev-4b-v2":0.9701753887049274,"open/robojev-4b-v3@0.25":0.9820137619972229,"open/robojev-4b-v3@0.5":0.9933071494252242,"open/robojev-4b-v3@0.75":0.9924673890431385,"open/robojev-4b-v3":0.990239133001503,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.7953548016750199,"respan/span-02":0.22462432,"typesafe/jev-1.13":0.78,"JEV-27B-VL (10 frames)":0.8013668356104371,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.703125}},{"suite":"so101","id":"tool_removal/pi0.5/eval_debug_task_cell_1_08h09m_30-jun-2026/ep000013","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000013","predictions":{"RoboJev-27B":0.02633420531918971,"GPT-6 Astra":0.07,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.06,"JEV-27B-VL":0.08896674640754589,"TypeSafe Jev 1.14":0.07,"Perplexity Decider":0.03334103476738888,"Liquid D1":0.1645164628965632,"Mercury Decide":0.02931223212930141,"Cloudflare Clef":0.2597,"cloudflare/clef-flash":0.264,"cloudflare/clef-omni":0.2096,"liquid/d1-ultra":0.22546161194543257,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.016668980937273314,"open/robojev-27b":null,"open/robojev-4b-v2":0.01929224350793923,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.04924136119799765,"open/robojev-4b-v3@0.75":0.02297736967873775,"open/robojev-4b-v3":0.012769726034700673,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.1624546348046551,"respan/span-02":0.24602316,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.2451508379938012,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.029296875}},{"suite":"so101","id":"tool_removal/pi0.5/eval_debug_task_cell_1_08h09m_30-jun-2026/ep000014","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000014","predictions":{"RoboJev-27B":0.007268862317956019,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.026570089446807724,"TypeSafe Jev 1.14":0.13,"Perplexity Decider":0.023880614402482635,"Liquid D1":0.22270014398423357,"Mercury Decide":0.010986943237791098,"Cloudflare Clef":0.154,"cloudflare/clef-flash":0.2175,"cloudflare/clef-omni":0.1456,"liquid/d1-ultra":0.20868888535414218,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.006904444753284513,"open/robojev-27b":null,"open/robojev-4b-v2":0.010419816599485524,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.03164395527984847,"open/robojev-4b-v3@0.75":0.0171641516746209,"open/robojev-4b-v3":0.008764341864947102,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.09456916185865796,"respan/span-02":0.25912672,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.04770785345160076,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0194091796875}},{"suite":"so101","id":"tool_removal/smolvla/eval_debug_task_cell_1_09h27m_26-jun-2026/ep000000","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000000","predictions":{"RoboJev-27B":0.030766776605290286,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.74,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":0.12217282403074736,"TypeSafe Jev 1.14":0.17,"Perplexity Decider":0.03292403778273221,"Liquid D1":0.34864513533394575,"Mercury Decide":0.025957354230854587,"Cloudflare Clef":0.2882,"cloudflare/clef-flash":0.3912,"cloudflare/clef-omni":0.3549,"liquid/d1-ultra":0.3790348222438061,"open/intern-decision-4b":0.43758935794935333,"open/robojev-27b-v1@0.5":0.018121519717420747,"open/robojev-27b":null,"open/robojev-4b-v2":0.20762754743879291,"open/robojev-4b-v3@0.25":0.4073334336280823,"open/robojev-4b-v3@0.5":0.2007555371763571,"open/robojev-4b-v3@0.75":0.08463674788192488,"open/robojev-4b-v3":0.03155642361885442,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.30920945819689744,"respan/span-02":0.19813901,"typesafe/jev-1.13":0.24,"JEV-27B-VL (10 frames)":0.2303363010315875,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0693359375}},{"suite":"so101","id":"tool_removal/smolvla/eval_debug_task_cell_1_09h27m_26-jun-2026/ep000001","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"success","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000001","predictions":{"RoboJev-27B":0.9851611284766093,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.8810435946519568,"TypeSafe Jev 1.14":0.62,"Perplexity Decider":0.8330352337352975,"Liquid D1":0.9669140225647107,"Mercury Decide":0.9914225160831462,"Cloudflare Clef":0.7739,"cloudflare/clef-flash":0.533,"cloudflare/clef-omni":0.4595,"liquid/d1-ultra":0.8553419792760201,"open/intern-decision-4b":0.778122175998967,"open/robojev-27b-v1@0.5":0.9773101617884609,"open/robojev-27b":null,"open/robojev-4b-v2":0.9881046720916962,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.9933071494252242,"open/robojev-4b-v3@0.75":0.9933071492776461,"open/robojev-4b-v3":0.991235658135053,"openai/gpt-6-luna-decisions":0.8,"perplexity/pplx-decider-flash-v1.2":0.8879497998877595,"respan/span-02":0.87145734,"typesafe/jev-1.13":0.76,"JEV-27B-VL (10 frames)":0.7191981095453702,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.5703125}},{"suite":"so101","id":"tool_removal/smolvla/eval_debug_task_cell_1_09h27m_26-jun-2026/ep000004","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000004","predictions":{"RoboJev-27B":0.010029983551676827,"GPT-6 Astra":0.07,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.07401602221842074,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.03644835612564309,"Liquid D1":0.24508500210441886,"Mercury Decide":0.03308597803117354,"Cloudflare Clef":0.1742,"cloudflare/clef-flash":0.2736,"cloudflare/clef-omni":0.1695,"liquid/d1-ultra":0.14465802218023963,"open/intern-decision-4b":0.37709365395745764,"open/robojev-27b-v1@0.5":0.0075355020892626055,"open/robojev-27b":null,"open/robojev-4b-v2":0.009125637690971435,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.05241435048719427,"open/robojev-4b-v3@0.75":0.019292242704938834,"open/robojev-4b-v3":0.01146957225399579,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.1674323289547967,"respan/span-02":0.22259186,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.12016317405563749,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.03173828125}},{"suite":"so101","id":"tool_removal/smolvla/eval_debug_task_cell_1_09h27m_26-jun-2026/ep000012","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000012","predictions":{"RoboJev-27B":0.04341386015302952,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.050092326151984154,"TypeSafe Jev 1.14":0.07,"Perplexity Decider":0.028479644349090696,"Liquid D1":0.23370635157681105,"Mercury Decide":0.025957356962325234,"Cloudflare Clef":0.2654,"cloudflare/clef-flash":0.3198,"cloudflare/clef-omni":0.1124,"liquid/d1-ultra":0.20868887757980986,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.006064308328063053,"open/robojev-27b":null,"open/robojev-4b-v2":0.011895327908303815,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.04625107524610428,"open/robojev-4b-v3@0.75":0.020451257661610673,"open/robojev-4b-v3":0.012102416042214261,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.11576469728028234,"respan/span-02":0.24775025,"typesafe/jev-1.13":0.13,"JEV-27B-VL (10 frames)":0.22507407564434323,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0272216796875}},{"suite":"so101","id":"tool_removal/smolvla/eval_debug_task_cell_1_09h27m_26-jun-2026/ep000016","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000016","predictions":{"RoboJev-27B":0.03038346530796914,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.07507876683691982,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.04125540612456734,"Liquid D1":0.2689414272294874,"Mercury Decide":0.02595736021183377,"Cloudflare Clef":0.1761,"cloudflare/clef-flash":0.2815,"cloudflare/clef-omni":0.1754,"liquid/d1-ultra":0.23419874690463163,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.011801388408780832,"open/robojev-27b":null,"open/robojev-4b-v2":0.014826107129937436,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.08060089942949411,"open/robojev-4b-v3@0.75":0.02435227726532882,"open/robojev-4b-v3":0.010869457225645628,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.19340209715054116,"respan/span-02":0.20350774,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.09355896831574255,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.04541015625}},{"suite":"so101","id":"tool_removal/smolvla/eval_debug_task_cell_1_09h27m_26-jun-2026/ep000022","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000022","predictions":{"RoboJev-27B":0.020931254758047028,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.03871380674031203,"TypeSafe Jev 1.14":0.17,"Perplexity Decider":0.027950447841235505,"Liquid D1":0.24508500210441886,"Mercury Decide":0.022977368781012936,"Cloudflare Clef":0.1427,"cloudflare/clef-flash":0.289,"cloudflare/clef-omni":0.2565,"liquid/d1-ultra":0.21695809190875665,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.007274636053928763,"open/robojev-27b":null,"open/robojev-4b-v2":0.016188347137528064,"open/robojev-4b-v3@0.25":0.18242551386356354,"open/robojev-4b-v3@0.5":0.0671334948723516,"open/robojev-4b-v3@0.75":0.02580728323952834,"open/robojev-4b-v3":0.013473327870331066,"openai/gpt-6-luna-decisions":0.06,"perplexity/pplx-decider-flash-v1.2":0.21949381949030772,"respan/span-02":0.14556861,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.07822090139376654,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.033203125}},{"suite":"so101","id":"tool_removal/smolvla/eval_debug_task_cell_1_09h27m_26-jun-2026/ep000024","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000024","predictions":{"RoboJev-27B":0.02112027940396091,"GPT-6 Astra":0.74,"GPT-6.1 Sol":0.65,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.13875488695089483,"TypeSafe Jev 1.14":0.16,"Perplexity Decider":0.04990468749295808,"Liquid D1":0.5926665999540697,"Mercury Decide":0.03732689136002139,"Cloudflare Clef":0.2661,"cloudflare/clef-flash":0.3278,"cloudflare/clef-omni":0.3495,"liquid/d1-ultra":0.4507950668241079,"open/intern-decision-4b":0.3201997500236374,"open/robojev-27b-v1@0.5":0.01863990917217876,"open/robojev-27b":null,"open/robojev-4b-v2":0.01691491336048918,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.11512034374911738,"open/robojev-4b-v3@0.75":0.07585818674635426,"open/robojev-4b-v3":0.04100570699541391,"openai/gpt-6-luna-decisions":0.11,"perplexity/pplx-decider-flash-v1.2":0.29250825556607724,"respan/span-02":0.55425525,"typesafe/jev-1.13":0.3,"JEV-27B-VL (10 frames)":0.18715220531054175,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.04541015625}},{"suite":"so101","id":"tool_removal/smolvla/eval_debug_task_cell_1_09h27m_26-jun-2026/ep000027","task":"Remove the small middle tool (3/8 Extension Bar 75mm) from the toolbox","label":"failure","scored":true,"source":"armnet/armnetbench_v01_robometer","group":"tool_removal","episode":"ep000027","predictions":{"RoboJev-27B":0.009150372432906659,"GPT-6 Astra":0.76,"GPT-6.1 Sol":0.12,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.07091034369800418,"TypeSafe Jev 1.14":0.14,"Perplexity Decider":0.03172413178200901,"Liquid D1":0.24508502416032488,"Mercury Decide":0.02595735653847632,"Cloudflare Clef":0.1458,"cloudflare/clef-flash":0.2972,"cloudflare/clef-omni":0.1563,"liquid/d1-ultra":0.13865650944890526,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.015314083321645616,"open/robojev-27b":null,"open/robojev-4b-v2":0.01691491336048918,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.06312881727672377,"open/robojev-4b-v3@0.75":0.032519444419615386,"open/robojev-4b-v3":0.020659669708358676,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.17025254882182606,"respan/span-02":0.16345952,"typesafe/jev-1.13":0.17,"JEV-27B-VL (10 frames)":0.1276385540943649,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.03564453125}},{"suite":"unseen","id":"rbm-ood/mit_franka/000c9dd6-e04c-4ee5-8af4-3abf3314c673","task":"Fold the towel in half","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"000c9dd6-e04c-4ee5-8af4-3abf3314c673","predictions":{"RoboJev-27B":0.04855545204771218,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.06459043597655864,"TypeSafe Jev 1.14":0.5,"Perplexity Decider":0.07151409602899908,"Liquid D1":0.46879062662624377,"Mercury Decide":0.025957356444287677,"Cloudflare Clef":0.2001,"cloudflare/clef-flash":0.3418,"cloudflare/clef-omni":0.151,"liquid/d1-ultra":0.15087378139605873,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.009959007232085459,"open/robojev-27b":null,"open/robojev-4b-v2":0.7532592839990138,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.0671334948723516,"open/robojev-4b-v3@0.75":0.048513171421607396,"open/robojev-4b-v3":0.02693677718853674,"openai/gpt-6-luna-decisions":0.06,"perplexity/pplx-decider-flash-v1.2":0.28407300716744904,"respan/span-02":0.1824107,"typesafe/jev-1.13":0.26,"JEV-27B-VL (10 frames)":0.07443176044050971,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.040283203125}},{"suite":"unseen","id":"rbm-ood/mit_franka/0151e02c-f5c5-43a6-be60-3bc377b6500f","task":"Pick up the spoon and place it inside the cup","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"0151e02c-f5c5-43a6-be60-3bc377b6500f","predictions":{"RoboJev-27B":0.010532211608223192,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.008720922174091386,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.013346593037292067,"Liquid D1":0.006289901252088071,"Mercury Decide":0.0021827160051876237,"Cloudflare Clef":0.0993,"cloudflare/clef-flash":0.1604,"cloudflare/clef-omni":0.0831,"liquid/d1-ultra":0.07129505533921282,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.001240653787452919,"open/robojev-27b":null,"open/robojev-4b-v2":0.0020145213081092066,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.007626874902958847,"open/robojev-4b-v3@0.75":0.00442228498579546,"open/robojev-4b-v3":0.002816147667248498,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.08304769213727932,"respan/span-02":0.15747161,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.005437733188752716,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.021240234375}},{"suite":"unseen","id":"rbm-ood/mit_franka/01baeffb-0ef4-4921-994f-e1c52a902d09","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"01baeffb-0ef4-4921-994f-e1c52a902d09","predictions":{"RoboJev-27B":0.0022590452362248733,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.004960321069758027,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.010448418377287372,"Liquid D1":0.031143830984404503,"Mercury Decide":0.0008559004710862784,"Cloudflare Clef":0.0702,"cloudflare/clef-flash":0.1868,"cloudflare/clef-omni":0.0998,"liquid/d1-ultra":0.07811527742431464,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.00021710774154949685,"open/robojev-27b":null,"open/robojev-4b-v2":0.004106490957182719,"open/robojev-4b-v3@0.25":0.014063626527786255,"open/robojev-4b-v3@0.5":0.007144725422878838,"open/robojev-4b-v3@0.75":0.007990902377034759,"open/robojev-4b-v3":0.006007651396687169,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.11835951869154576,"respan/span-02":0.08767896,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.010591642734884048,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00057220458984375}},{"suite":"unseen","id":"rbm-ood/mit_franka/01e3be9a-96b0-45b4-a15d-9827a50ba098","task":"Fold the towel in half","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"01e3be9a-96b0-45b4-a15d-9827a50ba098","predictions":{"RoboJev-27B":0.21056828871651925,"GPT-6 Astra":0.22,"GPT-6.1 Sol":0.36,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.3974365301113748,"TypeSafe Jev 1.14":0.49,"Perplexity Decider":0.3233395165315836,"Liquid D1":0.679178699175393,"Mercury Decide":0.37754066879814546,"Cloudflare Clef":0.2679,"cloudflare/clef-flash":0.3496,"cloudflare/clef-omni":0.1859,"liquid/d1-ultra":0.17794899629641256,"open/intern-decision-4b":0.37709365395745764,"open/robojev-27b-v1@0.5":0.1505139929758436,"open/robojev-27b":null,"open/robojev-4b-v2":0.2998075748777713,"open/robojev-4b-v3@0.25":0.3486451506614685,"open/robojev-4b-v3@0.5":0.1368024864039654,"open/robojev-4b-v3@0.75":0.08013780136639623,"open/robojev-4b-v3":0.04100570699541391,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.35743346183540026,"respan/span-02":0.2635809,"typesafe/jev-1.13":0.47,"JEV-27B-VL (10 frames)":0.30379657627535445,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0023956298828125}},{"suite":"unseen","id":"rbm-ood/mit_franka/03132b75-d5b5-469c-a51d-91d2adcb2e42","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"03132b75-d5b5-469c-a51d-91d2adcb2e42","predictions":{"RoboJev-27B":0.15049118002261913,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.3163793090345333,"TypeSafe Jev 1.14":0.15,"Perplexity Decider":0.23086692416380877,"Liquid D1":0.06371499069622688,"Mercury Decide":0.037326884666868405,"Cloudflare Clef":0.2749,"cloudflare/clef-flash":0.6151,"cloudflare/clef-omni":0.1792,"liquid/d1-ultra":0.11671092522468417,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.012673133441680001,"open/robojev-27b":null,"open/robojev-4b-v2":0.004106490957182719,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.01664357488299338,"open/robojev-4b-v3@0.75":0.012802394334981567,"open/robojev-4b-v3":0.010300413398065098,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.22722743387285915,"respan/span-02":0.10044435,"typesafe/jev-1.13":0.15,"JEV-27B-VL (10 frames)":0.25066437335110464,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00347900390625}},{"suite":"unseen","id":"rbm-ood/mit_franka/03249d25-4221-4b43-bc21-c72bb3846592","task":"Pick up the spatula and stir the beans in the pot","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"03249d25-4221-4b43-bc21-c72bb3846592","predictions":{"RoboJev-27B":0.5240908477628711,"GPT-6 Astra":0.93,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.68,"JEV-27B-VL":0.2537802056572498,"TypeSafe Jev 1.14":0.41,"Perplexity Decider":0.23663137882714014,"Liquid D1":0.6791786861878392,"Mercury Decide":0.11920291263495983,"Cloudflare Clef":0.3785,"cloudflare/clef-flash":0.456,"cloudflare/clef-omni":0.1506,"liquid/d1-ultra":0.6551469107189953,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.16243486766293425,"open/robojev-27b":null,"open/robojev-4b-v2":0.0790476748344352,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.1292175522858696,"open/robojev-4b-v3@0.75":0.24398537221615502,"open/robojev-4b-v3":0.367378816897974,"openai/gpt-6-luna-decisions":0.26,"perplexity/pplx-decider-flash-v1.2":0.451527012656243,"respan/span-02":0.73265845,"typesafe/jev-1.13":0.36,"JEV-27B-VL (10 frames)":0.27110194679587335,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0179443359375}},{"suite":"unseen","id":"rbm-ood/mit_franka/05538a11-c296-466f-8865-e4e3c0ea5d58","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"05538a11-c296-466f-8865-e4e3c0ea5d58","predictions":{"RoboJev-27B":0.5544925447772743,"GPT-6 Astra":0.91,"GPT-6.1 Sol":0.91,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.33326852330933276,"TypeSafe Jev 1.14":0.42,"Perplexity Decider":0.39939132474798744,"Liquid D1":0.880797068590724,"Mercury Decide":0.5621765008857981,"Cloudflare Clef":0.3038,"cloudflare/clef-flash":0.2706,"cloudflare/clef-omni":0.1125,"liquid/d1-ultra":0.74763213616082,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.7405182114263241,"open/robojev-27b":null,"open/robojev-4b-v2":0.8863079914043754,"open/robojev-4b-v3@0.25":0.9149009585380554,"open/robojev-4b-v3@0.5":0.9286271325815819,"open/robojev-4b-v3@0.75":0.8892726892788834,"open/robojev-4b-v3":0.863871653255755,"openai/gpt-6-luna-decisions":0.23,"perplexity/pplx-decider-flash-v1.2":0.7274036025492578,"respan/span-02":0.26140162,"typesafe/jev-1.13":0.52,"JEV-27B-VL (10 frames)":0.4860914398724602,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.40625}},{"suite":"unseen","id":"rbm-ood/mit_franka/06ff8c90-0541-47c1-8445-c51cf92b665b","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"06ff8c90-0541-47c1-8445-c51cf92b665b","predictions":{"RoboJev-27B":0.19966030529803727,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.2394724120357783,"TypeSafe Jev 1.14":0.21,"Perplexity Decider":0.20215940121855425,"Liquid D1":0.9149009491921662,"Mercury Decide":0.06008664933244599,"Cloudflare Clef":0.5108,"cloudflare/clef-flash":0.7173,"cloudflare/clef-omni":0.5798,"liquid/d1-ultra":0.25236786828046404,"open/intern-decision-4b":0.8089141677995819,"open/robojev-27b-v1@0.5":0.010217196641036902,"open/robojev-27b":null,"open/robojev-4b-v2":0.005361080321059209,"open/robojev-4b-v3@0.25":0.851952850818634,"open/robojev-4b-v3@0.5":0.1709446101989739,"open/robojev-4b-v3@0.75":0.09432751595727837,"open/robojev-4b-v3":0.0721349360304201,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3379557021560989,"respan/span-02":0.7702074,"typesafe/jev-1.13":0.46,"JEV-27B-VL (10 frames)":0.24904784066765245,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.09521484375}},{"suite":"unseen","id":"rbm-ood/mit_franka/07091ac9-b6b3-4a05-bf89-f414182ed8a8","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"07091ac9-b6b3-4a05-bf89-f414182ed8a8","predictions":{"RoboJev-27B":0.5681303469657835,"GPT-6 Astra":0.6,"GPT-6.1 Sol":0.64,"Claude Opus 5.5":0.42,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.24087800688650385,"TypeSafe Jev 1.14":0.29,"Perplexity Decider":0.26026054867464365,"Liquid D1":0.754914975839675,"Mercury Decide":0.46879062662624377,"Cloudflare Clef":0.3052,"cloudflare/clef-flash":0.4398,"cloudflare/clef-omni":0.5497,"liquid/d1-ultra":0.42648958363704076,"open/intern-decision-4b":0.39193998888916504,"open/robojev-27b-v1@0.5":0.4381146832308318,"open/robojev-27b":null,"open/robojev-4b-v2":0.6614231852142245,"open/robojev-4b-v3@0.25":0.622459352016449,"open/robojev-4b-v3@0.5":0.6877183043672045,"open/robojev-4b-v3@0.75":0.721593736224953,"open/robojev-4b-v3":0.4324801789491653,"openai/gpt-6-luna-decisions":0.08,"perplexity/pplx-decider-flash-v1.2":0.42896746708265826,"respan/span-02":0.71400213,"typesafe/jev-1.13":0.36,"JEV-27B-VL (10 frames)":0.2456384860435432,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.027587890625}},{"suite":"unseen","id":"rbm-ood/mit_franka/07b1ec0d-0aec-4b55-a0be-a3d7428bea47","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"07b1ec0d-0aec-4b55-a0be-a3d7428bea47","predictions":{"RoboJev-27B":0.2403409122395357,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.07,"JEV-27B-VL":0.3845988394307721,"TypeSafe Jev 1.14":0.22,"Perplexity Decider":0.0996512930645882,"Liquid D1":0.980875963668392,"Mercury Decide":0.07585817270885642,"Cloudflare Clef":0.3699,"cloudflare/clef-flash":0.2354,"cloudflare/clef-omni":0.5966,"liquid/d1-ultra":0.16396263221794186,"open/intern-decision-4b":0.6518947636686268,"open/robojev-27b-v1@0.5":0.43997301972055763,"open/robojev-27b":null,"open/robojev-4b-v2":0.006402505190256269,"open/robojev-4b-v3@0.25":0.9465966820716858,"open/robojev-4b-v3@0.5":0.9286271325815819,"open/robojev-4b-v3@0.75":0.22270014231977903,"open/robojev-4b-v3":0.14942342283990945,"openai/gpt-6-luna-decisions":0.82,"perplexity/pplx-decider-flash-v1.2":0.6859619869073197,"respan/span-02":0.645376,"typesafe/jev-1.13":0.47,"JEV-27B-VL (10 frames)":0.299680526264096,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00885009765625}},{"suite":"unseen","id":"rbm-ood/mit_franka/07ba1444-4ea6-45c7-9b2c-3b74a1fdb49f","task":"Pick up the spatula and stir the beans in the pot","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"07ba1444-4ea6-45c7-9b2c-3b74a1fdb49f","predictions":{"RoboJev-27B":0.6596000941468261,"GPT-6 Astra":0.9,"GPT-6.1 Sol":0.86,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.41789200243302316,"TypeSafe Jev 1.14":0.42,"Perplexity Decider":0.3078302557765791,"Liquid D1":0.7981867729389246,"Mercury Decide":0.22270014914315833,"Cloudflare Clef":0.5001,"cloudflare/clef-flash":0.4249,"cloudflare/clef-omni":0.2704,"liquid/d1-ultra":0.450795090135065,"open/intern-decision-4b":0.45308504361568214,"open/robojev-27b-v1@0.5":0.6619968732523599,"open/robojev-27b":null,"open/robojev-4b-v2":0.1381957315129781,"open/robojev-4b-v3@0.25":0.8354835510253906,"open/robojev-4b-v3@0.5":0.846904551172507,"open/robojev-4b-v3@0.75":0.8564010309387029,"open/robojev-4b-v3":0.8505765771600906,"openai/gpt-6-luna-decisions":0.19,"perplexity/pplx-decider-flash-v1.2":0.5546341933964419,"respan/span-02":0.35212258,"typesafe/jev-1.13":0.37,"JEV-27B-VL (10 frames)":0.5400565769115765,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.337890625}},{"suite":"unseen","id":"rbm-ood/mit_franka/07bd8aa3-9565-4931-a1ae-2b57622a89eb","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"07bd8aa3-9565-4931-a1ae-2b57622a89eb","predictions":{"RoboJev-27B":0.0017511800163456375,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.004255166123305434,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.011617592209807178,"Liquid D1":0.01590639474411069,"Mercury Decide":0.0012448430774543477,"Cloudflare Clef":0.0537,"cloudflare/clef-flash":0.1511,"cloudflare/clef-omni":0.1627,"liquid/d1-ultra":0.059277252317696164,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.00044037874173443576,"open/robojev-27b":null,"open/robojev-4b-v2":0.002876746893908692,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.0037133326112963453,"open/robojev-4b-v3@0.75":0.0032876613688676065,"open/robojev-4b-v3":0.0033132012876683184,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.059917510839654665,"respan/span-02":0.14928026,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.0021204420083318475,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000518798828125}},{"suite":"unseen","id":"rbm-ood/mit_franka/0c1d3d91-a9f0-423e-af58-34d61b90f7cd","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"0c1d3d91-a9f0-423e-af58-34d61b90f7cd","predictions":{"RoboJev-27B":0.2732338782695436,"GPT-6 Astra":0.22,"GPT-6.1 Sol":0.24,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.7432014053632262,"TypeSafe Jev 1.14":0.62,"Perplexity Decider":0.801418404363114,"Liquid D1":0.8175744806385543,"Mercury Decide":0.9324533088603709,"Cloudflare Clef":0.5068,"cloudflare/clef-flash":0.3959,"cloudflare/clef-omni":0.4306,"liquid/d1-ultra":0.6770986984253415,"open/intern-decision-4b":0.7439389554145914,"open/robojev-27b-v1@0.5":0.924673706062587,"open/robojev-27b":null,"open/robojev-4b-v2":0.003593602817215226,"open/robojev-4b-v3@0.25":0.9241418242454529,"open/robojev-4b-v3@0.5":0.19040689770918212,"open/robojev-4b-v3@0.75":0.06424971259337996,"open/robojev-4b-v3":0.03693826366802302,"openai/gpt-6-luna-decisions":0.08,"perplexity/pplx-decider-flash-v1.2":0.8206588678531022,"respan/span-02":0.78106844,"typesafe/jev-1.13":0.68,"JEV-27B-VL (10 frames)":0.6495162898969304,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.64453125}},{"suite":"unseen","id":"rbm-ood/mit_franka/0e067172-7a09-42b1-a71a-2ff359818496","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"0e067172-7a09-42b1-a71a-2ff359818496","predictions":{"RoboJev-27B":0.8039063691813565,"GPT-6 Astra":0.93,"GPT-6.1 Sol":0.91,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.7357828571185032,"TypeSafe Jev 1.14":0.68,"Perplexity Decider":0.7898919203524876,"Liquid D1":0.8354835411997897,"Mercury Decide":0.7981867873410141,"Cloudflare Clef":0.4408,"cloudflare/clef-flash":0.6543,"cloudflare/clef-omni":0.3905,"liquid/d1-ultra":0.8671346890896433,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.9039649053316273,"open/robojev-27b":null,"open/robojev-4b-v2":0.0017624512139676404,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.05241435048719427,"open/robojev-4b-v3@0.75":0.028975397327291364,"open/robojev-4b-v3":0.01499717745111633,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.7155661002155247,"respan/span-02":0.15291734,"typesafe/jev-1.13":0.73,"JEV-27B-VL (10 frames)":0.8373385067052441,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.053466796875}},{"suite":"unseen","id":"rbm-ood/mit_franka/0ee0335f-aa12-44dd-acd1-8344c231604b","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"0ee0335f-aa12-44dd-acd1-8344c231604b","predictions":{"RoboJev-27B":0.47047525258645606,"GPT-6 Astra":0.2,"GPT-6.1 Sol":0.12,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.659744941970862,"TypeSafe Jev 1.14":0.44,"Perplexity Decider":0.5869814016125864,"Liquid D1":0.899121388082479,"Mercury Decide":0.7981867825403176,"Cloudflare Clef":0.5958,"cloudflare/clef-flash":0.675,"cloudflare/clef-omni":0.2362,"liquid/d1-ultra":0.3790348333243961,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.6137585265359492,"open/robojev-27b":null,"open/robojev-4b-v2":0.002106299096066607,"open/robojev-4b-v3@0.25":0.3775406777858734,"open/robojev-4b-v3@0.5":0.10858632498619036,"open/robojev-4b-v3@0.75":0.08013780136639623,"open/robojev-4b-v3":0.053129261209546814,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.5244227447787311,"respan/span-02":0.90306,"typesafe/jev-1.13":0.53,"JEV-27B-VL (10 frames)":0.6905753745732401,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.019775390625}},{"suite":"unseen","id":"rbm-ood/mit_franka/10ffeb3c-19b2-400a-9112-570fcaa5902a","task":"Pour the pebbles from the cup onto the plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"10ffeb3c-19b2-400a-9112-570fcaa5902a","predictions":{"RoboJev-27B":0.6426672453498546,"GPT-6 Astra":0.15,"GPT-6.1 Sol":0.14,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.27627437873606614,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.14578253937101654,"Liquid D1":0.9149009526726544,"Mercury Decide":0.37754066879814546,"Cloudflare Clef":0.4205,"cloudflare/clef-flash":0.4181,"cloudflare/clef-omni":0.204,"liquid/d1-ultra":0.5,"open/intern-decision-4b":0.7318060856600669,"open/robojev-27b-v1@0.5":0.834165674549482,"open/robojev-27b":null,"open/robojev-4b-v2":0.014826107129937436,"open/robojev-4b-v3@0.25":0.9046505093574524,"open/robojev-4b-v3@0.5":0.22270012535630726,"open/robojev-4b-v3@0.75":0.1669856712343507,"open/robojev-4b-v3":0.12384396710192513,"openai/gpt-6-luna-decisions":0.76,"perplexity/pplx-decider-flash-v1.2":0.4141598204689335,"respan/span-02":0.8162518,"typesafe/jev-1.13":0.23,"JEV-27B-VL (10 frames)":0.37517933262242564,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.07080078125}},{"suite":"unseen","id":"rbm-ood/mit_franka/12354cbd-8e8e-4be6-80d8-c388fe9e1059","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"12354cbd-8e8e-4be6-80d8-c388fe9e1059","predictions":{"RoboJev-27B":0.0674774175516463,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.0636659372381661,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.0814148511823079,"Liquid D1":0.5926665855647394,"Mercury Decide":0.01098694330863086,"Cloudflare Clef":0.3534,"cloudflare/clef-flash":0.6218,"cloudflare/clef-omni":0.2073,"liquid/d1-ultra":0.09784416068877341,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.001960866149894293,"open/robojev-27b":null,"open/robojev-4b-v2":0.005128210097528264,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.02450159025746704,"open/robojev-4b-v3@0.75":0.006692850722353873,"open/robojev-4b-v3":0.006007651396687169,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.11706974515728222,"respan/span-02":0.21770032,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.13443954624192422,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.28125}},{"suite":"unseen","id":"rbm-ood/mit_franka/12ae16fd-d749-4a57-b6c3-9b8d4f08749d","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"12ae16fd-d749-4a57-b6c3-9b8d4f08749d","predictions":{"RoboJev-27B":0.7836282482441491,"GPT-6 Astra":0.77,"GPT-6.1 Sol":0.72,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.2537802056572498,"TypeSafe Jev 1.14":0.41,"Perplexity Decider":0.2908882040161121,"Liquid D1":0.46879062662624377,"Mercury Decide":0.18242552380635632,"Cloudflare Clef":0.2155,"cloudflare/clef-flash":0.3707,"cloudflare/clef-omni":0.1824,"liquid/d1-ultra":0.3674872816095884,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.4866966271418196,"open/robojev-27b":null,"open/robojev-4b-v2":0.6411495733195756,"open/robojev-4b-v3@0.25":0.531209409236908,"open/robojev-4b-v3@0.5":0.37137657841700994,"open/robojev-4b-v3@0.75":0.22270014231977903,"open/robojev-4b-v3":0.13612834674424493,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.3853396479015999,"respan/span-02":0.38040316,"typesafe/jev-1.13":0.36,"JEV-27B-VL (10 frames)":0.49277205994189605,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0223388671875}},{"suite":"unseen","id":"rbm-ood/mit_franka/12c4b30a-4d5c-47cf-99da-aa4cd73433f7","task":"Pick up the spoon and place it inside the cup","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"12c4b30a-4d5c-47cf-99da-aa4cd73433f7","predictions":{"RoboJev-27B":0.8557659864947879,"GPT-6 Astra":0.87,"GPT-6.1 Sol":0.87,"Claude Opus 5.5":0.7,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.37012243697994074,"TypeSafe Jev 1.14":0.18,"Perplexity Decider":0.4349691400796599,"Liquid D1":0.6224593312018546,"Mercury Decide":0.8354835350552604,"Cloudflare Clef":0.2021,"cloudflare/clef-flash":0.7575,"cloudflare/clef-omni":0.1185,"liquid/d1-ultra":0.6325127183904117,"open/intern-decision-4b":0.43758935794935333,"open/robojev-27b-v1@0.5":0.8408675230619385,"open/robojev-27b":null,"open/robojev-4b-v2":0.17977728828192718,"open/robojev-4b-v3@0.25":0.9046505093574524,"open/robojev-4b-v3@0.5":0.9662767595980272,"open/robojev-4b-v3@0.75":0.9818023083761724,"open/robojev-4b-v3":0.9804117628234067,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.5194591892561043,"respan/span-02":0.8174508,"typesafe/jev-1.13":0.35,"JEV-27B-VL (10 frames)":0.6408583828795137,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.267578125}},{"suite":"unseen","id":"rbm-ood/mit_franka/132839cd-841c-480e-940c-9c22d34dd355","task":"Pour the pebbles from the cup onto the plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"132839cd-841c-480e-940c-9c22d34dd355","predictions":{"RoboJev-27B":0.5793390007911723,"GPT-6 Astra":0.9,"GPT-6.1 Sol":0.87,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.29834604757917593,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.36698532652853944,"Liquid D1":0.8175744806385543,"Mercury Decide":0.3486451421018059,"Cloudflare Clef":0.6325,"cloudflare/clef-flash":0.6648,"cloudflare/clef-omni":0.2502,"liquid/d1-ultra":0.6982966473937054,"open/intern-decision-4b":0.7557061813028185,"open/robojev-27b-v1@0.5":0.6376993802604727,"open/robojev-27b":null,"open/robojev-4b-v2":0.01691491336048918,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.9683560447201516,"open/robojev-4b-v3@0.75":0.9320774407500154,"open/robojev-4b-v3":0.8573531996579977,"openai/gpt-6-luna-decisions":0.17,"perplexity/pplx-decider-flash-v1.2":0.5753231050771861,"respan/span-02":0.7884314,"typesafe/jev-1.13":0.18,"JEV-27B-VL (10 frames)":0.2795944490950705,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.34765625}},{"suite":"unseen","id":"rbm-ood/mit_franka/13fe84df-e15f-46b5-b912-7469492471cd","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"13fe84df-e15f-46b5-b912-7469492471cd","predictions":{"RoboJev-27B":0.00636837030945131,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.011431998340266121,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.022948538386347743,"Liquid D1":0.32082130082460697,"Mercury Decide":0.0029810321734815566,"Cloudflare Clef":0.3265,"cloudflare/clef-flash":0.3277,"cloudflare/clef-omni":0.1498,"liquid/d1-ultra":0.11671093129122209,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.0005678242109250436,"open/robojev-27b":null,"open/robojev-4b-v2":0.005361080321059209,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.059347834814291,"open/robojev-4b-v3@0.75":0.04090405663501426,"open/robojev-4b-v3":0.04100570699541391,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.2543850408887335,"respan/span-02":0.07700461,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.005105416437381794,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00537109375}},{"suite":"unseen","id":"rbm-ood/mit_franka/14a26a41-f949-4c2a-aced-4d5d0b9f6f6f","task":"Fold the towel in half","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"14a26a41-f949-4c2a-aced-4d5d0b9f6f6f","predictions":{"RoboJev-27B":0.13451921830686517,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.17,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.28247681749584524,"TypeSafe Jev 1.14":0.38,"Perplexity Decider":0.2560325252203904,"Liquid D1":0.34864513533394575,"Mercury Decide":0.16451645675203383,"Cloudflare Clef":0.3031,"cloudflare/clef-flash":0.3494,"cloudflare/clef-omni":0.1417,"liquid/d1-ultra":0.17794900318310736,"open/intern-decision-4b":0.34810523633137336,"open/robojev-27b-v1@0.5":0.10702896687847943,"open/robojev-27b":null,"open/robojev-4b-v2":0.16698566684595678,"open/robojev-4b-v3@0.25":0.22270014882087708,"open/robojev-4b-v3@0.5":0.07137286741841814,"open/robojev-4b-v3@0.75":0.03444519627897428,"open/robojev-4b-v3":0.016690455215260983,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.45527901696425266,"respan/span-02":0.7145466,"typesafe/jev-1.13":0.34,"JEV-27B-VL (10 frames)":0.18447548667273944,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01068115234375}},{"suite":"unseen","id":"rbm-ood/mit_franka/14b766d5-7a47-4730-ad93-433a92162563","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"14b766d5-7a47-4730-ad93-433a92162563","predictions":{"RoboJev-27B":0.9670590847813707,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.8777765378472143,"TypeSafe Jev 1.14":0.46,"Perplexity Decider":0.9644248583462187,"Liquid D1":0.9740426412951848,"Mercury Decide":0.9953904274146709,"Cloudflare Clef":0.851,"cloudflare/clef-flash":0.8005,"cloudflare/clef-omni":0.9351,"liquid/d1-ultra":0.7830419160891692,"open/intern-decision-4b":0.8748864949022742,"open/robojev-27b-v1@0.5":0.9656986013146419,"open/robojev-27b":null,"open/robojev-4b-v2":0.008730681628235537,"open/robojev-4b-v3@0.25":0.9875683188438416,"open/robojev-4b-v3@0.5":0.7152565465994749,"open/robojev-4b-v3@0.75":0.21256653766057104,"open/robojev-4b-v3":0.13612834674424493,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.7155148543661166,"respan/span-02":0.66699636,"typesafe/jev-1.13":0.53,"JEV-27B-VL (10 frames)":0.8704563699275998,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.349609375}},{"suite":"unseen","id":"rbm-ood/mit_franka/15b63612-8916-4023-8f13-f7fb29add5df","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"15b63612-8916-4023-8f13-f7fb29add5df","predictions":{"RoboJev-27B":0.2488544670942283,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.3298544683989705,"TypeSafe Jev 1.14":0.17,"Perplexity Decider":0.2065490505420508,"Liquid D1":0.89330940889474,"Mercury Decide":0.08509905138791504,"Cloudflare Clef":0.6032,"cloudflare/clef-flash":0.7625,"cloudflare/clef-omni":0.1976,"liquid/d1-ultra":0.15730751148838965,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.04717692109866683,"open/robojev-27b":null,"open/robojev-4b-v2":0.002631674205642126,"open/robojev-4b-v3@0.25":0.10669060051441193,"open/robojev-4b-v3@0.5":0.020201721614979237,"open/robojev-4b-v3@0.75":0.008476838215708002,"open/robojev-4b-v3":0.0074556149068047885,"openai/gpt-6-luna-decisions":0.84,"perplexity/pplx-decider-flash-v1.2":0.08257371808707453,"respan/span-02":0.22384766,"typesafe/jev-1.13":0.22,"JEV-27B-VL (10 frames)":0.3418931474599229,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.51171875}},{"suite":"unseen","id":"rbm-ood/mit_franka/15e57e62-b420-43b2-9700-a2dd2e4bf790","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"15e57e62-b420-43b2-9700-a2dd2e4bf790","predictions":{"RoboJev-27B":0.43987675268357473,"GPT-6 Astra":0.18,"GPT-6.1 Sol":0.12,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.261142212739024,"TypeSafe Jev 1.14":0.23,"Perplexity Decider":0.07122546688748481,"Liquid D1":0.8933094046341532,"Mercury Decide":0.20181322946142374,"Cloudflare Clef":0.5705,"cloudflare/clef-flash":0.5123,"cloudflare/clef-omni":0.2395,"liquid/d1-ultra":0.2254616160560029,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.3181111011453435,"open/robojev-27b":null,"open/robojev-4b-v2":0.006996270681650968,"open/robojev-4b-v3@0.25":0.7549149990081787,"open/robojev-4b-v3@0.5":0.4345875784292984,"open/robojev-4b-v3@0.75":0.1754304037756096,"open/robojev-4b-v3":0.14942342283990945,"openai/gpt-6-luna-decisions":0.86,"perplexity/pplx-decider-flash-v1.2":0.3796249634821024,"respan/span-02":0.61657447,"typesafe/jev-1.13":0.38,"JEV-27B-VL (10 frames)":0.1261751491994034,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1328125}},{"suite":"unseen","id":"rbm-ood/mit_franka/15f075e4-d639-4a40-949e-199a0e5dafcd","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"15f075e4-d639-4a40-949e-199a0e5dafcd","predictions":{"RoboJev-27B":0.4683532870835299,"GPT-6 Astra":0.84,"GPT-6.1 Sol":0.91,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.5191871981766353,"TypeSafe Jev 1.14":0.14,"Perplexity Decider":0.6161036192546543,"Liquid D1":0.22270013882530884,"Mercury Decide":0.5,"Cloudflare Clef":0.2766,"cloudflare/clef-flash":0.2685,"cloudflare/clef-omni":0.1584,"liquid/d1-ultra":0.4264895951521023,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.7282658378565742,"open/robojev-27b":null,"open/robojev-4b-v2":0.0034372413231743533,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.02612421708095358,"open/robojev-4b-v3@0.75":0.0143976132495814,"open/robojev-4b-v3":0.008764341864947102,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.3371604796889259,"respan/span-02":0.21247193,"typesafe/jev-1.13":0.18,"JEV-27B-VL (10 frames)":0.6517826051625787,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.002716064453125}},{"suite":"unseen","id":"rbm-ood/mit_franka/196c6353-4dc2-4af0-b65c-a758e7e45345","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"196c6353-4dc2-4af0-b65c-a758e7e45345","predictions":{"RoboJev-27B":0.07704680261328647,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.07779720424896532,"TypeSafe Jev 1.14":0.13,"Perplexity Decider":0.125421614488184,"Liquid D1":0.7310585786300049,"Mercury Decide":0.02297736857193652,"Cloudflare Clef":0.5174,"cloudflare/clef-flash":0.6083,"cloudflare/clef-omni":0.6567,"liquid/d1-ultra":0.09357237882026911,"open/intern-decision-4b":0.5313278281391198,"open/robojev-27b-v1@0.5":0.0026828143783736913,"open/robojev-27b":null,"open/robojev-4b-v2":0.004488287139460313,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.007144725422878838,"open/robojev-4b-v3@0.75":0.0032876613688676065,"open/robojev-4b-v3":0.0022671624120110317,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.15129688946377098,"respan/span-02":0.8366849,"typesafe/jev-1.13":0.19,"JEV-27B-VL (10 frames)":0.17942231948365978,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00180816650390625}},{"suite":"unseen","id":"rbm-ood/mit_franka/1975e479-961e-459e-be6f-5eae24900626","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"1975e479-961e-459e-be6f-5eae24900626","predictions":{"RoboJev-27B":0.9623811421430677,"GPT-6 Astra":0.93,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.9170456869250513,"TypeSafe Jev 1.14":0.8,"Perplexity Decider":0.9747464146379864,"Liquid D1":0.9706877710505719,"Mercury Decide":0.9940889319755869,"Cloudflare Clef":0.7815,"cloudflare/clef-flash":0.7731,"cloudflare/clef-omni":0.3236,"liquid/d1-ultra":0.822051010590282,"open/intern-decision-4b":0.8748864949022742,"open/robojev-27b-v1@0.5":0.9881519068893191,"open/robojev-27b":null,"open/robojev-4b-v2":0.16698566684595678,"open/robojev-4b-v3@0.25":0.9820137619972229,"open/robojev-4b-v3@0.5":0.9662767595980272,"open/robojev-4b-v3@0.75":0.5,"open/robojev-4b-v3":0.20445237038006636,"openai/gpt-6-luna-decisions":0.99,"perplexity/pplx-decider-flash-v1.2":0.9526888132247806,"respan/span-02":0.76438034,"typesafe/jev-1.13":0.86,"JEV-27B-VL (10 frames)":0.9346747091913113,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.609375}},{"suite":"unseen","id":"rbm-ood/mit_franka/1d9930d7-eb19-4d96-96ba-f3fdcdb2fe72","task":"Pick up the spatula and stir the beans in the pot","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"1d9930d7-eb19-4d96-96ba-f3fdcdb2fe72","predictions":{"RoboJev-27B":0.7409347624141697,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.5707097153683564,"TypeSafe Jev 1.14":0.67,"Perplexity Decider":0.3869525583441238,"Liquid D1":0.8354835411997897,"Mercury Decide":0.7772998611746911,"Cloudflare Clef":0.7228,"cloudflare/clef-flash":0.718,"cloudflare/clef-omni":0.672,"liquid/d1-ultra":0.687795908116423,"open/intern-decision-4b":0.5313278281391198,"open/robojev-27b-v1@0.5":0.8577883378091542,"open/robojev-27b":null,"open/robojev-4b-v2":0.9456867326137218,"open/robojev-4b-v3@0.25":0.9465966820716858,"open/robojev-4b-v3@0.5":0.9507586388020023,"open/robojev-4b-v3@0.75":0.9392374795976737,"open/robojev-4b-v3":0.8978823160759336,"openai/gpt-6-luna-decisions":0.77,"perplexity/pplx-decider-flash-v1.2":0.7703758929568629,"respan/span-02":0.8251209,"typesafe/jev-1.13":0.47,"JEV-27B-VL (10 frames)":0.5663987475815072,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.032470703125}},{"suite":"unseen","id":"rbm-ood/mit_franka/1de13c1d-4b72-437f-a1ed-4050f85f6557","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"1de13c1d-4b72-437f-a1ed-4050f85f6557","predictions":{"RoboJev-27B":0.9242347070185809,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.9598090523414199,"TypeSafe Jev 1.14":0.84,"Perplexity Decider":0.9387397345746411,"Liquid D1":0.994088931669123,"Mercury Decide":0.9980732657468011,"Cloudflare Clef":0.8704,"cloudflare/clef-flash":0.7202,"cloudflare/clef-omni":0.7378,"liquid/d1-ultra":0.9064276062060482,"open/intern-decision-4b":0.7439389554145914,"open/robojev-27b-v1@0.5":0.9903775961365096,"open/robojev-27b":null,"open/robojev-4b-v2":0.04392481517503748,"open/robojev-4b-v3@0.25":0.9740425944328308,"open/robojev-4b-v3@0.5":0.9442201868171092,"open/robojev-4b-v3@0.75":0.8411309059812064,"open/robojev-4b-v3":0.7865658074141403,"openai/gpt-6-luna-decisions":0.98,"perplexity/pplx-decider-flash-v1.2":0.9400479391653617,"respan/span-02":0.94821495,"typesafe/jev-1.13":0.87,"JEV-27B-VL (10 frames)":0.9473525967790516,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.330078125}},{"suite":"unseen","id":"rbm-ood/mit_franka/20b51c66-336b-42df-a619-da72b8501547","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"20b51c66-336b-42df-a619-da72b8501547","predictions":{"RoboJev-27B":0.000990241937332237,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.005607224210906416,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.014592819163079264,"Liquid D1":0.06008665101556925,"Mercury Decide":0.001325022297671513,"Cloudflare Clef":0.0778,"cloudflare/clef-flash":0.1806,"cloudflare/clef-omni":0.1437,"liquid/d1-ultra":0.03883945094042057,"open/intern-decision-4b":0.09461348765523125,"open/robojev-27b-v1@0.5":0.0008536755554672943,"open/robojev-27b":null,"open/robojev-4b-v2":0.0014746525778226533,"open/robojev-4b-v3@0.25":0.006692850962281227,"open/robojev-4b-v3@0.5":0.0023461481126818818,"open/robojev-4b-v3@0.75":0.0016121526329810115,"open/robojev-4b-v3":0.0012482263663496401,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.04104074378530023,"respan/span-02":0.14582334,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.002470853131831897,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00070953369140625}},{"suite":"unseen","id":"rbm-ood/mit_franka/22bde85d-a824-42c1-8c11-3ce96dc30b29","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"22bde85d-a824-42c1-8c11-3ce96dc30b29","predictions":{"RoboJev-27B":0.4450595249498298,"GPT-6 Astra":0.73,"GPT-6.1 Sol":0.84,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.6279698438585501,"TypeSafe Jev 1.14":0.64,"Perplexity Decider":0.507394489904604,"Liquid D1":0.9648551541045004,"Mercury Decide":0.46879062662624377,"Cloudflare Clef":0.501,"cloudflare/clef-flash":0.4737,"cloudflare/clef-omni":0.2696,"liquid/d1-ultra":0.37903481116321625,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.49146529490560276,"open/robojev-27b":null,"open/robojev-4b-v2":0.007644678711335276,"open/robojev-4b-v3@0.25":0.8807970285415649,"open/robojev-4b-v3@0.5":0.22270012535630726,"open/robojev-4b-v3@0.75":0.1050005837572588,"open/robojev-4b-v3":0.04319701644612397,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.7106257531596413,"respan/span-02":0.09806954,"typesafe/jev-1.13":0.54,"JEV-27B-VL (10 frames)":0.6672140326535627,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.462890625}},{"suite":"unseen","id":"rbm-ood/mit_franka/235d3093-4796-4f84-baa9-ce18d6ff1a49","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"235d3093-4796-4f84-baa9-ce18d6ff1a49","predictions":{"RoboJev-27B":0.018832072329807305,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.00865458790093593,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.030104959333134576,"Liquid D1":0.37754066879814546,"Mercury Decide":0.002182716483884326,"Cloudflare Clef":0.2845,"cloudflare/clef-flash":0.3386,"cloudflare/clef-omni":0.1261,"liquid/d1-ultra":0.08552782318603236,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.001249259455375735,"open/robojev-27b":null,"open/robojev-4b-v2":0.01138187822152329,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.11512034374911738,"open/robojev-4b-v3@0.75":0.08463674788192488,"open/robojev-4b-v3":0.06518962178801281,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.306674645916616,"respan/span-02":0.15202683,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.018775528574928632,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006683349609375}},{"suite":"unseen","id":"rbm-ood/mit_franka/23667b25-131a-44c6-aa31-9413c4a18a7a","task":"Pull a tissue from the tissue box","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"23667b25-131a-44c6-aa31-9413c4a18a7a","predictions":{"RoboJev-27B":0.9537860575042598,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8344137624907007,"TypeSafe Jev 1.14":0.74,"Perplexity Decider":0.8231851941014636,"Liquid D1":0.9783846675524838,"Mercury Decide":0.9525741308615412,"Cloudflare Clef":0.6141,"cloudflare/clef-flash":0.7281,"cloudflare/clef-omni":0.6008,"liquid/d1-ultra":0.6877959081164229,"open/intern-decision-4b":0.637525577991227,"open/robojev-27b-v1@0.5":0.9867149828184664,"open/robojev-27b":null,"open/robojev-4b-v2":0.87699602202752,"open/robojev-4b-v3@0.25":0.9046505093574524,"open/robojev-4b-v3@0.5":0.9090947575586418,"open/robojev-4b-v3@0.75":0.8489244915244398,"open/robojev-4b-v3":0.7677504278026662,"openai/gpt-6-luna-decisions":0.93,"perplexity/pplx-decider-flash-v1.2":0.7502723277807672,"respan/span-02":0.966791,"typesafe/jev-1.13":0.68,"JEV-27B-VL (10 frames)":0.888761120355863,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.046630859375}},{"suite":"unseen","id":"rbm-ood/mit_franka/23c242da-0437-4224-aeb5-9d2d021d40a6","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"23c242da-0437-4224-aeb5-9d2d021d40a6","predictions":{"RoboJev-27B":0.3555709226282537,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.5422027347558217,"TypeSafe Jev 1.14":0.35,"Perplexity Decider":0.6697520149705358,"Liquid D1":0.7772998611746911,"Mercury Decide":0.5,"Cloudflare Clef":0.4447,"cloudflare/clef-flash":0.5621,"cloudflare/clef-omni":0.4241,"liquid/d1-ultra":0.6662128387243579,"open/intern-decision-4b":0.45308504361568214,"open/robojev-27b-v1@0.5":0.2920093938233108,"open/robojev-27b":null,"open/robojev-4b-v2":0.0031445701339940513,"open/robojev-4b-v3@0.25":0.531209409236908,"open/robojev-4b-v3@0.5":0.05577981318289087,"open/robojev-4b-v3@0.75":0.02580728323952834,"open/robojev-4b-v3":0.012102416042214261,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.6919850045324576,"respan/span-02":0.89157903,"typesafe/jev-1.13":0.52,"JEV-27B-VL (10 frames)":0.4493832485361469,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.166015625}},{"suite":"unseen","id":"rbm-ood/mit_franka/23c5eeec-16a3-4cbd-9614-ea3ae9a47771","task":"Pull a tissue from the tissue box","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"23c5eeec-16a3-4cbd-9614-ea3ae9a47771","predictions":{"RoboJev-27B":0.9633125575073379,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.9416007082994379,"TypeSafe Jev 1.14":0.85,"Perplexity Decider":0.945099635009651,"Liquid D1":0.962673116404036,"Mercury Decide":0.9924227585570545,"Cloudflare Clef":0.8539,"cloudflare/clef-flash":0.6437,"cloudflare/clef-omni":0.6784,"liquid/d1-ultra":0.910531394053345,"open/intern-decision-4b":0.5469149563843178,"open/robojev-27b-v1@0.5":0.9872757670139884,"open/robojev-27b":null,"open/robojev-4b-v2":0.26370774468711267,"open/robojev-4b-v3@0.25":0.9525741338729858,"open/robojev-4b-v3@0.5":0.9442201868171092,"open/robojev-4b-v3@0.75":0.8769960242027004,"open/robojev-4b-v3":0.527147193867567,"openai/gpt-6-luna-decisions":0.93,"perplexity/pplx-decider-flash-v1.2":0.8868635310767073,"respan/span-02":0.6268051,"typesafe/jev-1.13":0.9,"JEV-27B-VL (10 frames)":0.9661279783814299,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.376953125}},{"suite":"unseen","id":"rbm-ood/mit_franka/2515bfa2-44b9-4b19-b088-876ff875801d","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"2515bfa2-44b9-4b19-b088-876ff875801d","predictions":{"RoboJev-27B":0.18788402300712245,"GPT-6 Astra":0.74,"GPT-6.1 Sol":0.06,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.31305701944092784,"TypeSafe Jev 1.14":0.18,"Perplexity Decider":0.17870310360600408,"Liquid D1":0.7772998663336157,"Mercury Decide":0.29421496597446145,"Cloudflare Clef":0.4781,"cloudflare/clef-flash":0.4229,"cloudflare/clef-omni":0.2727,"liquid/d1-ultra":0.30170333772886615,"open/intern-decision-4b":0.3201997500236374,"open/robojev-27b-v1@0.5":0.13195576874362447,"open/robojev-27b":null,"open/robojev-4b-v2":0.009125637690971435,"open/robojev-4b-v3@0.25":0.7310585379600525,"open/robojev-4b-v3@0.5":0.3122816956327956,"open/robojev-4b-v3@0.75":0.24398537221615502,"open/robojev-4b-v3":0.13612834674424493,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.4066226464952693,"respan/span-02":0.81817687,"typesafe/jev-1.13":0.09,"JEV-27B-VL (10 frames)":0.1429659107076276,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00628662109375}},{"suite":"unseen","id":"rbm-ood/mit_franka/26242dd7-a9a6-4290-bb00-30f206f97876","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"26242dd7-a9a6-4290-bb00-30f206f97876","predictions":{"RoboJev-27B":0.030729629000102832,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.015610948711065262,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.04750050701317087,"Liquid D1":0.24508500210441886,"Mercury Decide":0.012431652270995075,"Cloudflare Clef":0.2362,"cloudflare/clef-flash":0.2475,"cloudflare/clef-omni":0.0732,"liquid/d1-ultra":0.081745034490993,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.001446729583426144,"open/robojev-27b":null,"open/robojev-4b-v2":0.003757049695787553,"open/robojev-4b-v3@0.25":0.07585817575454712,"open/robojev-4b-v3@0.5":0.03164395527984847,"open/robojev-4b-v3@0.75":0.02580728323952834,"open/robojev-4b-v3":0.024229601278625137,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.20780534506993265,"respan/span-02":0.04140614,"typesafe/jev-1.13":0.09,"JEV-27B-VL (10 frames)":0.025392067921318005,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00433349609375}},{"suite":"unseen","id":"rbm-ood/mit_franka/29dc44e8-3ae1-4849-aa0f-8efb7e2c6e04","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"29dc44e8-3ae1-4849-aa0f-8efb7e2c6e04","predictions":{"RoboJev-27B":0.08942462794678654,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.08,"JEV-27B-VL":0.2537802056572498,"TypeSafe Jev 1.14":0.16,"Perplexity Decider":0.11172605379559698,"Liquid D1":0.02931222905542399,"Mercury Decide":0.033085974694221476,"Cloudflare Clef":0.3051,"cloudflare/clef-flash":0.2254,"cloudflare/clef-omni":0.1793,"liquid/d1-ultra":0.09357238930184676,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.15189718453344078,"open/robojev-27b":null,"open/robojev-4b-v2":0.0023025598229782147,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.01664357488299338,"open/robojev-4b-v3@0.75":0.007100415903386552,"open/robojev-4b-v3":0.0048395274167548985,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2439471306824685,"respan/span-02":0.09983026,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.221574332059768,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.021240234375}},{"suite":"unseen","id":"rbm-ood/mit_franka/2a8163c8-03ee-4b29-99a1-c6849c349d13","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"2a8163c8-03ee-4b29-99a1-c6849c349d13","predictions":{"RoboJev-27B":0.5895978410082077,"GPT-6 Astra":0.05,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.6835185788186595,"TypeSafe Jev 1.14":0.42,"Perplexity Decider":0.719614590636057,"Liquid D1":0.9399133540338004,"Mercury Decide":0.731058584489497,"Cloudflare Clef":0.5732,"cloudflare/clef-flash":0.6395,"cloudflare/clef-omni":0.5417,"liquid/d1-ultra":0.5369560013004135,"open/intern-decision-4b":0.8275619327448428,"open/robojev-27b-v1@0.5":0.6669432414512293,"open/robojev-27b":null,"open/robojev-4b-v2":0.004293165515526464,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.1804712758005596,"open/robojev-4b-v3@0.75":0.0458382546620802,"open/robojev-4b-v3":0.017606235547797083,"openai/gpt-6-luna-decisions":0.84,"perplexity/pplx-decider-flash-v1.2":0.9265164631707583,"respan/span-02":0.88968706,"typesafe/jev-1.13":0.61,"JEV-27B-VL (10 frames)":0.7445154266463296,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.37109375}},{"suite":"unseen","id":"rbm-ood/mit_franka/2bc5e41a-f2f9-469e-9c61-edea17686a67","task":"Pour the pebbles from the cup onto the plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"2bc5e41a-f2f9-469e-9c61-edea17686a67","predictions":{"RoboJev-27B":0.8973108143947651,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.6152894211454202,"TypeSafe Jev 1.14":0.76,"Perplexity Decider":0.823344628665487,"Liquid D1":0.6513548646660542,"Mercury Decide":0.9706877671817261,"Cloudflare Clef":0.3522,"cloudflare/clef-flash":0.291,"cloudflare/clef-omni":0.222,"liquid/d1-ultra":0.8491262216195331,"open/intern-decision-4b":0.3201997500236374,"open/robojev-27b-v1@0.5":0.9843455742487693,"open/robojev-27b":null,"open/robojev-4b-v2":0.010419816599485524,"open/robojev-4b-v3@0.25":0.9046505093574524,"open/robojev-4b-v3@0.5":0.9662767595980272,"open/robojev-4b-v3@0.75":0.9566958954509301,"open/robojev-4b-v3":0.9241418172849298,"openai/gpt-6-luna-decisions":0.17,"perplexity/pplx-decider-flash-v1.2":0.5132572565185207,"respan/span-02":0.32726336,"typesafe/jev-1.13":0.83,"JEV-27B-VL (10 frames)":0.7838434963388738,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006103515625}},{"suite":"unseen","id":"rbm-ood/mit_franka/2d3e8649-ef2a-4e08-97c3-e7df066a7e7e","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"2d3e8649-ef2a-4e08-97c3-e7df066a7e7e","predictions":{"RoboJev-27B":0.8278938897394722,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.7768718518621963,"TypeSafe Jev 1.14":0.28,"Perplexity Decider":0.8405897858742779,"Liquid D1":0.3486451421018059,"Mercury Decide":0.9525741232882133,"Cloudflare Clef":0.3144,"cloudflare/clef-flash":0.2505,"cloudflare/clef-omni":0.086,"liquid/d1-ultra":0.8426924947523362,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.9722259043473153,"open/robojev-27b":null,"open/robojev-4b-v2":0.002106299096066607,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.0909052424413583,"open/robojev-4b-v3@0.75":0.1107273107211166,"open/robojev-4b-v3":0.10211768392406631,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3540787738349797,"respan/span-02":0.21873127,"typesafe/jev-1.13":0.47,"JEV-27B-VL (10 frames)":0.7306147318829097,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.337890625}},{"suite":"unseen","id":"rbm-ood/mit_franka/2da3ac9d-c65a-4b97-af12-4836a9a06c0d","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"2da3ac9d-c65a-4b97-af12-4836a9a06c0d","predictions":{"RoboJev-27B":0.3547663396256921,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.06,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.557453014194743,"TypeSafe Jev 1.14":0.47,"Perplexity Decider":0.5828945446837355,"Liquid D1":0.9465966739665496,"Mercury Decide":0.32082130082460697,"Cloudflare Clef":0.6375,"cloudflare/clef-flash":0.7754,"cloudflare/clef-omni":0.4211,"liquid/d1-ultra":0.3229012912817457,"open/intern-decision-4b":0.608060011110835,"open/robojev-27b-v1@0.5":0.18912707608655527,"open/robojev-27b":null,"open/robojev-4b-v2":0.005361080321059209,"open/robojev-4b-v3@0.25":0.5,"open/robojev-4b-v3@0.5":0.08060089942949411,"open/robojev-4b-v3@0.75":0.027346787282274982,"open/robojev-4b-v3":0.013473327870331066,"openai/gpt-6-luna-decisions":0.48,"perplexity/pplx-decider-flash-v1.2":0.39948580859566984,"respan/span-02":0.1651603,"typesafe/jev-1.13":0.47,"JEV-27B-VL (10 frames)":0.6365069866029881,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.054931640625}},{"suite":"unseen","id":"rbm-ood/mit_franka/2e5d1a5a-314f-4931-acfe-8a97816ac4ce","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"2e5d1a5a-314f-4931-acfe-8a97816ac4ce","predictions":{"RoboJev-27B":0.978334218283583,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.9541065140500102,"TypeSafe Jev 1.14":0.81,"Perplexity Decider":0.9777586968077572,"Liquid D1":0.9579122677288678,"Mercury Decide":0.9902915238498219,"Cloudflare Clef":0.6853,"cloudflare/clef-flash":0.6319,"cloudflare/clef-omni":0.4092,"liquid/d1-ultra":0.8832890772019308,"open/intern-decision-4b":0.788764540067536,"open/robojev-27b-v1@0.5":0.9937015971991979,"open/robojev-27b":null,"open/robojev-4b-v2":0.03251944279343901,"open/robojev-4b-v3@0.25":0.9740425944328308,"open/robojev-4b-v3@0.5":0.972148766331303,"open/robojev-4b-v3@0.75":0.9425470270820971,"open/robojev-4b-v3":0.8505765771600906,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9272533664996242,"respan/span-02":0.27430448,"typesafe/jev-1.13":0.81,"JEV-27B-VL (10 frames)":0.974280410304008,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.6015625}},{"suite":"unseen","id":"rbm-ood/mit_franka/2ebe5d8d-a81f-4626-95de-1941c78f3a23","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"2ebe5d8d-a81f-4626-95de-1941c78f3a23","predictions":{"RoboJev-27B":0.0009620053699163477,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0005317435479659549,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.010093559272579811,"Liquid D1":0.022977369240981062,"Mercury Decide":0.0004583128724766983,"Cloudflare Clef":0.1097,"cloudflare/clef-flash":0.173,"cloudflare/clef-omni":0.1338,"liquid/d1-ultra":0.04917794980351907,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":0.00019385502371388773,"open/robojev-27b":null,"open/robojev-4b-v2":0.0012900470555811355,"open/robojev-4b-v3@0.25":0.005220125894993544,"open/robojev-4b-v3@0.5":0.002505290630348441,"open/robojev-4b-v3@0.75":0.0019267347489025771,"open/robojev-4b-v3":0.0012482263663496401,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.044028904620147365,"respan/span-02":0.28280085,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.0035467756777348286,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000644683837890625}},{"suite":"unseen","id":"rbm-ood/mit_franka/2f3fb3c1-4d80-4737-8da3-6113c4566ab6","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"2f3fb3c1-4d80-4737-8da3-6113c4566ab6","predictions":{"RoboJev-27B":0.022320160593354878,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.005859650213304702,"TypeSafe Jev 1.14":0.02,"Perplexity Decider":0.00679324159156739,"Liquid D1":0.021615333077779054,"Mercury Decide":0.0005527785942175576,"Cloudflare Clef":0.0507,"cloudflare/clef-flash":0.1519,"cloudflare/clef-omni":0.1113,"liquid/d1-ultra":0.0469203871306772,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.0004905653272107419,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016121527751335812,"open/robojev-4b-v3@0.25":0.01798621006309986,"open/robojev-4b-v3@0.5":0.009275566578748366,"open/robojev-4b-v3@0.75":0.005946149584938689,"open/robojev-4b-v3":0.002816147667248498,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.03545683555608444,"respan/span-02":0.08480118,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.011351587479262092,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0284423828125}},{"suite":"unseen","id":"rbm-ood/mit_franka/2f8ded58-2c09-4aea-bb90-a74d7b67a151","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"2f8ded58-2c09-4aea-bb90-a74d7b67a151","predictions":{"RoboJev-27B":0.12697869462384545,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.22438394650011112,"TypeSafe Jev 1.14":0.2,"Perplexity Decider":0.2377456085166424,"Liquid D1":0.4378234991142019,"Mercury Decide":0.06008665143635008,"Cloudflare Clef":0.4005,"cloudflare/clef-flash":0.3691,"cloudflare/clef-omni":0.4463,"liquid/d1-ultra":0.3122040817744257,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.024378871467843257,"open/robojev-27b":null,"open/robojev-4b-v2":0.001842766452331557,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.008690106319066306,"open/robojev-4b-v3@0.75":0.004692235822472068,"open/robojev-4b-v3":0.0033132012876683184,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.15169045959942157,"respan/span-02":0.16274495,"typesafe/jev-1.13":0.19,"JEV-27B-VL (10 frames)":0.24587794618320946,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2392578125}},{"suite":"unseen","id":"rbm-ood/mit_franka/2f98b96c-ea1d-419f-bda1-e5af330d80f6","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"2f98b96c-ea1d-419f-bda1-e5af330d80f6","predictions":{"RoboJev-27B":0.006879337482991524,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.01087982407066415,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.020113952314993515,"Liquid D1":0.05340332678672523,"Mercury Decide":0.0019267347009375125,"Cloudflare Clef":0.1992,"cloudflare/clef-flash":0.1619,"cloudflare/clef-omni":0.0924,"liquid/d1-ultra":0.16396261931118655,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.0007641308235474971,"open/robojev-27b":null,"open/robojev-4b-v2":0.008352675304716173,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.01560037702180545,"open/robojev-4b-v3@0.75":0.009538287541433899,"open/robojev-4b-v3":0.006341061537493235,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.10628996752299225,"respan/span-02":0.5562626,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.0199773326398609,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01068115234375}},{"suite":"unseen","id":"rbm-ood/mit_franka/30bffa61-10ef-4870-bc86-24ec5e05f2ed","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"30bffa61-10ef-4870-bc86-24ec5e05f2ed","predictions":{"RoboJev-27B":0.7955194292796601,"GPT-6 Astra":0.05,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.8333468168766098,"TypeSafe Jev 1.14":0.44,"Perplexity Decider":0.81902484429265,"Liquid D1":0.962673116404036,"Mercury Decide":0.9324533097989077,"Cloudflare Clef":0.8249,"cloudflare/clef-flash":0.8317,"cloudflare/clef-omni":0.8702,"liquid/d1-ultra":0.5855387537836041,"open/intern-decision-4b":0.767101934678807,"open/robojev-27b-v1@0.5":0.9509436832943204,"open/robojev-27b":null,"open/robojev-4b-v2":0.03700737584165394,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.12199371684192196,"open/robojev-4b-v3@0.75":0.054313266183183405,"open/robojev-4b-v3":0.024229601278625137,"openai/gpt-6-luna-decisions":0.25,"perplexity/pplx-decider-flash-v1.2":0.8656092906666804,"respan/span-02":0.8598222,"typesafe/jev-1.13":0.63,"JEV-27B-VL (10 frames)":0.8734196836001993,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.71875}},{"suite":"unseen","id":"rbm-ood/mit_franka/3580a08c-c530-4206-9adf-49696348cf63","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"3580a08c-c530-4206-9adf-49696348cf63","predictions":{"RoboJev-27B":0.028099762847663634,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.02057444538889519,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.07830331610684804,"Liquid D1":0.18242553269617778,"Mercury Decide":0.005220126883274219,"Cloudflare Clef":0.1418,"cloudflare/clef-flash":0.1906,"cloudflare/clef-omni":0.1177,"liquid/d1-ultra":0.1022889535537961,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.002878678131456087,"open/robojev-27b":null,"open/robojev-4b-v2":0.002106299096066607,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.003964844872971652,"open/robojev-4b-v3@0.75":0.0025929030441612317,"open/robojev-4b-v3":0.0020341273969387797,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.15050178069589212,"respan/span-02":0.5531381,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.03316295238126372,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.138671875}},{"suite":"unseen","id":"rbm-ood/mit_franka/35fa519b-3bbd-40ff-8b35-3d860eee6df2","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"35fa519b-3bbd-40ff-8b35-3d860eee6df2","predictions":{"RoboJev-27B":0.9239658710296605,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.67,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.9290585483310958,"TypeSafe Jev 1.14":0.62,"Perplexity Decider":0.9654080830322592,"Liquid D1":0.9770226314280634,"Mercury Decide":0.997199073078401,"Cloudflare Clef":0.8124,"cloudflare/clef-flash":0.8708,"cloudflare/clef-omni":0.8777,"liquid/d1-ultra":0.807146758249643,"open/intern-decision-4b":0.788764540067536,"open/robojev-27b-v1@0.5":0.9846309484473638,"open/robojev-27b":null,"open/robojev-4b-v2":0.006996270681650968,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.9770226296926641,"open/robojev-4b-v3@0.75":0.9541617453379198,"open/robojev-4b-v3":0.8874762480971222,"openai/gpt-6-luna-decisions":0.29,"perplexity/pplx-decider-flash-v1.2":0.879449808473827,"respan/span-02":0.7756431,"typesafe/jev-1.13":0.62,"JEV-27B-VL (10 frames)":0.8758201143000369,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.26171875}},{"suite":"unseen","id":"rbm-ood/mit_franka/362444b2-3b7e-4e0a-b025-23e6071c0944","task":"Pull a tissue from the tissue box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"362444b2-3b7e-4e0a-b025-23e6071c0944","predictions":{"RoboJev-27B":0.48289315960459495,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.06,"Claude Opus 5.5":0.25,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.2479901091861985,"TypeSafe Jev 1.14":0.15,"Perplexity Decider":0.281868386166822,"Liquid D1":0.3629692055196168,"Mercury Decide":0.08509903920620716,"Cloudflare Clef":0.4722,"cloudflare/clef-flash":0.3562,"cloudflare/clef-omni":0.3945,"liquid/d1-ultra":0.4144612690663902,"open/intern-decision-4b":0.34810523633137336,"open/robojev-27b-v1@0.5":0.10361546214172551,"open/robojev-27b":null,"open/robojev-4b-v2":0.2467407160009862,"open/robojev-4b-v3@0.25":0.10669060051441193,"open/robojev-4b-v3@0.5":0.07137286741841814,"open/robojev-4b-v3@0.75":0.06424971259337996,"open/robojev-4b-v3":0.07975708092262541,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.18669758028996308,"respan/span-02":0.18335617,"typesafe/jev-1.13":0.17,"JEV-27B-VL (10 frames)":0.2994199245072967,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00433349609375}},{"suite":"unseen","id":"rbm-ood/mit_franka/36585075-3c6d-4f06-b112-a90f84556cb4","task":"Pick up the spatula and stir the beans in the pot","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"36585075-3c6d-4f06-b112-a90f84556cb4","predictions":{"RoboJev-27B":0.6795109626885111,"GPT-6 Astra":0.92,"GPT-6.1 Sol":0.92,"Claude Opus 5.5":0.62,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.40669466132940313,"TypeSafe Jev 1.14":0.6,"Perplexity Decider":0.5195237025031595,"Liquid D1":0.8807970904940926,"Mercury Decide":0.22270014398423357,"Cloudflare Clef":0.6262,"cloudflare/clef-flash":0.6084,"cloudflare/clef-omni":0.3127,"liquid/d1-ultra":0.6209651888367838,"open/intern-decision-4b":0.5624106420506467,"open/robojev-27b-v1@0.5":0.8927014260825316,"open/robojev-27b":null,"open/robojev-4b-v2":0.7185943895092446,"open/robojev-4b-v3@0.25":0.7772998809814453,"open/robojev-4b-v3@0.5":0.846904551172507,"open/robojev-4b-v3@0.75":0.863567022376025,"open/robojev-4b-v3":0.863871653255755,"openai/gpt-6-luna-decisions":0.29,"perplexity/pplx-decider-flash-v1.2":0.30938467091591554,"respan/span-02":0.77497447,"typesafe/jev-1.13":0.4,"JEV-27B-VL (10 frames)":0.44125873327856047,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.255859375}},{"suite":"unseen","id":"rbm-ood/mit_franka/3677a3d6-b3b4-485e-a126-f6bb39b2ddbc","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"3677a3d6-b3b4-485e-a126-f6bb39b2ddbc","predictions":{"RoboJev-27B":0.002296870528862164,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.008251189841272698,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.023442049931642034,"Liquid D1":0.07159119746371433,"Mercury Decide":0.0038244835949623295,"Cloudflare Clef":0.1428,"cloudflare/clef-flash":0.1857,"cloudflare/clef-omni":0.1372,"liquid/d1-ultra":0.08946860307029417,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.0012063039237288882,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016856305131264125,"open/robojev-4b-v3@0.25":0.009708477184176445,"open/robojev-4b-v3@0.5":0.0032570072049156237,"open/robojev-4b-v3@0.75":0.0014314726301544898,"open/robojev-4b-v3":0.0005527786044704864,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.12793112493625441,"respan/span-02":0.089554235,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.016943726478725708,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0010986328125}},{"suite":"unseen","id":"rbm-ood/mit_franka/36f6efbe-618d-4f8a-9248-dfd418f622b2","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"36f6efbe-618d-4f8a-9248-dfd418f622b2","predictions":{"RoboJev-27B":0.029720554015696673,"GPT-6 Astra":0.06,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.06940304474576556,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.06784314963155623,"Liquid D1":0.2689414213699951,"Mercury Decide":0.025957358422249308,"Cloudflare Clef":0.3231,"cloudflare/clef-flash":0.3275,"cloudflare/clef-omni":0.1236,"liquid/d1-ultra":0.0894686049878681,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.008178760782875794,"open/robojev-27b":null,"open/robojev-4b-v2":0.002876746893908692,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.07137286741841814,"open/robojev-4b-v3@0.75":0.13643297762397494,"open/robojev-4b-v3":0.19575444983810342,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.35749917499757267,"respan/span-02":0.08974274,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.03808704122787996,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.103515625}},{"suite":"unseen","id":"rbm-ood/mit_franka/37c316ad-2fbf-47de-a713-bd63d7148a00","task":"Pull a tissue from the tissue box","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"37c316ad-2fbf-47de-a713-bd63d7148a00","predictions":{"RoboJev-27B":0.9231783046875853,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.872731345314592,"TypeSafe Jev 1.14":0.55,"Perplexity Decider":0.8419612853045825,"Liquid D1":0.8354835330070839,"Mercury Decide":0.9626731115849659,"Cloudflare Clef":0.5803,"cloudflare/clef-flash":0.5917,"cloudflare/clef-omni":0.3417,"liquid/d1-ultra":0.8491262306663081,"open/intern-decision-4b":0.5930110454411601,"open/robojev-27b-v1@0.5":0.9902789023781101,"open/robojev-27b":null,"open/robojev-4b-v2":0.8564010365978134,"open/robojev-4b-v3@0.25":0.8807970285415649,"open/robojev-4b-v3@0.5":0.9442201868171092,"open/robojev-4b-v3@0.75":0.9541617453379198,"open/robojev-4b-v3":0.9278650639695798,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.6276216280842983,"respan/span-02":0.87541634,"typesafe/jev-1.13":0.52,"JEV-27B-VL (10 frames)":0.7567514578191468,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2119140625}},{"suite":"unseen","id":"rbm-ood/mit_franka/37cba8cf-f5d7-4be2-80bb-749cd6b40afb","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"37cba8cf-f5d7-4be2-80bb-749cd6b40afb","predictions":{"RoboJev-27B":0.5841393624784268,"GPT-6 Astra":0.06,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.6868414494916286,"TypeSafe Jev 1.14":0.39,"Perplexity Decider":0.5220734556127888,"Liquid D1":0.9241418262465169,"Mercury Decide":0.7772998560157665,"Cloudflare Clef":0.4999,"cloudflare/clef-flash":0.3481,"cloudflare/clef-omni":0.5403,"liquid/d1-ultra":0.46304399869958657,"open/intern-decision-4b":0.6518947636686268,"open/robojev-27b-v1@0.5":0.8528301965199755,"open/robojev-27b":null,"open/robojev-4b-v2":0.021996220940774924,"open/robojev-4b-v3@0.25":0.8175744414329529,"open/robojev-4b-v3@0.5":0.25872010509521604,"open/robojev-4b-v3@0.75":0.09432751595727837,"open/robojev-4b-v3":0.053129261209546814,"openai/gpt-6-luna-decisions":0.81,"perplexity/pplx-decider-flash-v1.2":0.7413832005675866,"respan/span-02":0.7618531,"typesafe/jev-1.13":0.42,"JEV-27B-VL (10 frames)":0.5080272904667086,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.007110595703125}},{"suite":"unseen","id":"rbm-ood/mit_franka/39d6923e-647d-4007-ba43-3523a12cd0eb","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"39d6923e-647d-4007-ba43-3523a12cd0eb","predictions":{"RoboJev-27B":0.021459253785421857,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.011431998340266121,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.04183951377255347,"Liquid D1":0.29421497216298875,"Mercury Decide":0.007577242556483638,"Cloudflare Clef":0.2241,"cloudflare/clef-flash":0.7382,"cloudflare/clef-omni":0.812,"liquid/d1-ultra":0.1573075005671197,"open/intern-decision-4b":0.5,"open/robojev-27b-v1@0.5":0.0014823633008907264,"open/robojev-27b":null,"open/robojev-4b-v2":0.0020145213081092066,"open/robojev-4b-v3@0.25":0.03308597952127457,"open/robojev-4b-v3@0.5":0.007626874902958847,"open/robojev-4b-v3@0.75":0.005282311488788821,"open/robojev-4b-v3":0.0048395274167548985,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3357818518093145,"respan/span-02":0.81632894,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.08044012139122118,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.375}},{"suite":"unseen","id":"rbm-ood/mit_franka/3a8a20cc-3b5c-4866-94c0-46bd7e642c29","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"3a8a20cc-3b5c-4866-94c0-46bd7e642c29","predictions":{"RoboJev-27B":0.4989035080897203,"GPT-6 Astra":0.68,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.6492955835296644,"TypeSafe Jev 1.14":0.19,"Perplexity Decider":0.4479290811162935,"Liquid D1":0.7549149923816048,"Mercury Decide":0.16451645880021026,"Cloudflare Clef":0.4873,"cloudflare/clef-flash":0.4835,"cloudflare/clef-omni":0.2963,"liquid/d1-ultra":0.19285324175035704,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.3451661157362102,"open/robojev-27b":null,"open/robojev-4b-v2":0.02297736939860946,"open/robojev-4b-v3@0.25":0.29421496391296387,"open/robojev-4b-v3@0.5":0.1804712758005596,"open/robojev-4b-v3@0.75":0.0717892678456694,"open/robojev-4b-v3":0.03155642361885442,"openai/gpt-6-luna-decisions":0.97,"perplexity/pplx-decider-flash-v1.2":0.4048757421185473,"respan/span-02":0.24441406,"typesafe/jev-1.13":0.33,"JEV-27B-VL (10 frames)":0.7318693269290293,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0247802734375}},{"suite":"unseen","id":"rbm-ood/mit_franka/3b289cc8-0e0d-4431-a9e8-685430eac45b","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"3b289cc8-0e0d-4431-a9e8-685430eac45b","predictions":{"RoboJev-27B":0.38092537027038453,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.4235233470349467,"TypeSafe Jev 1.14":0.27,"Perplexity Decider":0.24472021556202808,"Liquid D1":0.8519528038477825,"Mercury Decide":0.10669058471438037,"Cloudflare Clef":0.2418,"cloudflare/clef-flash":0.7792,"cloudflare/clef-omni":0.2003,"liquid/d1-ultra":0.21695809990668272,"open/intern-decision-4b":0.5930110454411601,"open/robojev-27b-v1@0.5":0.201160034216275,"open/robojev-27b":null,"open/robojev-4b-v2":0.0025170615300917137,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.02612421708095358,"open/robojev-4b-v3@0.75":0.02580728323952834,"open/robojev-4b-v3":0.021788411170123766,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3265075267409931,"respan/span-02":0.12041,"typesafe/jev-1.13":0.43,"JEV-27B-VL (10 frames)":0.5022120212934187,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.28515625}},{"suite":"unseen","id":"rbm-ood/mit_franka/3b7ddb9b-ab1b-4088-8d85-41d331d59184","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"3b7ddb9b-ab1b-4088-8d85-41d331d59184","predictions":{"RoboJev-27B":0.4725509107016007,"GPT-6 Astra":0.18,"GPT-6.1 Sol":0.28,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.7357828571185032,"TypeSafe Jev 1.14":0.39,"Perplexity Decider":0.6959326961040161,"Liquid D1":0.8991213826762113,"Mercury Decide":0.7981867777396212,"Cloudflare Clef":0.8815,"cloudflare/clef-flash":0.8012,"cloudflare/clef-omni":0.3946,"liquid/d1-ultra":0.3448530892810048,"open/intern-decision-4b":0.8184242551251981,"open/robojev-27b-v1@0.5":0.3828424351146379,"open/robojev-27b":null,"open/robojev-4b-v2":0.0046922355486094065,"open/robojev-4b-v3@0.25":0.9669140577316284,"open/robojev-4b-v3@0.5":0.4184967522309292,"open/robojev-4b-v3@0.75":0.19332136802205585,"open/robojev-4b-v3":0.11806640532074496,"openai/gpt-6-luna-decisions":0.64,"perplexity/pplx-decider-flash-v1.2":0.7559772274886609,"respan/span-02":0.11458246,"typesafe/jev-1.13":0.24,"JEV-27B-VL (10 frames)":0.732532401370728,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00860595703125}},{"suite":"unseen","id":"rbm-ood/mit_franka/3ff3e7bd-a1c5-42da-979e-5cf52da01326","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"3ff3e7bd-a1c5-42da-979e-5cf52da01326","predictions":{"RoboJev-27B":0.9423772781045618,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.82,"JEV-27B-VL":0.9534272531522867,"TypeSafe Jev 1.14":0.83,"Perplexity Decider":0.9693312442976647,"Liquid D1":0.9770226309262801,"Mercury Decide":0.998073265395774,"Cloudflare Clef":0.7505,"cloudflare/clef-flash":0.6918,"cloudflare/clef-omni":0.6516,"liquid/d1-ultra":0.8360373806888134,"open/intern-decision-4b":0.637525577991227,"open/robojev-27b-v1@0.5":0.9835552112533541,"open/robojev-27b":null,"open/robojev-4b-v2":0.009969411693719354,"open/robojev-4b-v3@0.25":0.9669140577316284,"open/robojev-4b-v3@0.5":0.9368711827232762,"open/robojev-4b-v3@0.75":0.8066786319779442,"open/robojev-4b-v3":0.5135836153966654,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.8531903383743206,"respan/span-02":0.89263403,"typesafe/jev-1.13":0.78,"JEV-27B-VL (10 frames)":0.9476208564035347,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.33203125}},{"suite":"unseen","id":"rbm-ood/mit_franka/41288645-ddd4-46af-9402-d67c21b98227","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"41288645-ddd4-46af-9402-d67c21b98227","predictions":{"RoboJev-27B":0.822032974948262,"GPT-6 Astra":0.15,"GPT-6.1 Sol":0.15,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.8621068923576506,"TypeSafe Jev 1.14":0.71,"Perplexity Decider":0.8758219493684831,"Liquid D1":0.9830850847509661,"Mercury Decide":0.9399133531922388,"Cloudflare Clef":0.7575,"cloudflare/clef-flash":0.8358,"cloudflare/clef-omni":0.7903,"liquid/d1-ultra":0.7745383921651378,"open/intern-decision-4b":0.8527907640733415,"open/robojev-27b-v1@0.5":0.9443430616540992,"open/robojev-27b":null,"open/robojev-4b-v2":0.056652424895021994,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.9090947575586418,"open/robojev-4b-v3@0.75":0.4407557950301173,"open/robojev-4b-v3":0.20445237038006636,"openai/gpt-6-luna-decisions":0.9,"perplexity/pplx-decider-flash-v1.2":0.9543343663680536,"respan/span-02":0.8806608,"typesafe/jev-1.13":0.79,"JEV-27B-VL (10 frames)":0.8992307552741102,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.353515625}},{"suite":"unseen","id":"rbm-ood/mit_franka/42965aef-8c98-4cc9-a49c-d7f8a3a6d86e","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"42965aef-8c98-4cc9-a49c-d7f8a3a6d86e","predictions":{"RoboJev-27B":0.0060327463356360375,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.0005343081124150946,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.012606993060153568,"Liquid D1":0.027585285024786244,"Mercury Decide":0.0010322308792578018,"Cloudflare Clef":0.0748,"cloudflare/clef-flash":0.1708,"cloudflare/clef-omni":0.0612,"liquid/d1-ultra":0.06502832269022725,"open/intern-decision-4b":0.09461348765523125,"open/robojev-27b-v1@0.5":0.00011742742209052601,"open/robojev-27b":null,"open/robojev-4b-v2":0.056652424895021994,"open/robojev-4b-v3@0.25":0.01243165135383606,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.004692235822472068,"open/robojev-4b-v3":0.003897642342744068,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.06402535859319101,"respan/span-02":0.034951907,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.007306615976997138,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00093841552734375}},{"suite":"unseen","id":"rbm-ood/mit_franka/4411a010-2a24-47ae-a7b8-de61de38e8a0","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"4411a010-2a24-47ae-a7b8-de61de38e8a0","predictions":{"RoboJev-27B":0.047022892998555006,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.027378666728553335,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.044831014106830734,"Liquid D1":0.06754668550840877,"Mercury Decide":0.0179862088106142,"Cloudflare Clef":0.2431,"cloudflare/clef-flash":0.1781,"cloudflare/clef-omni":0.1654,"liquid/d1-ultra":0.13286531226634116,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.00558742275148399,"open/robojev-27b":null,"open/robojev-4b-v2":0.007644678711335276,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.10858632498619036,"open/robojev-4b-v3@0.75":0.18420778945962635,"open/robojev-4b-v3":0.25219182149741376,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.13810989652252925,"respan/span-02":0.09339451,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.07119640641651051,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00421142578125}},{"suite":"unseen","id":"rbm-ood/mit_franka/4596a95d-7900-4b36-b7ba-5782fab9b8c9","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"4596a95d-7900-4b36-b7ba-5782fab9b8c9","predictions":{"RoboJev-27B":0.9505329664029507,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.9,"Claude Sonnet 5.5":0.92,"JEV-27B-VL":0.9579879670428882,"TypeSafe Jev 1.14":0.81,"Perplexity Decider":0.9536726978383177,"Liquid D1":0.9859363728017917,"Mercury Decide":0.9933071500415868,"Cloudflare Clef":0.7292,"cloudflare/clef-flash":0.8076,"cloudflare/clef-omni":0.8258,"liquid/d1-ultra":0.9064276201814854,"open/intern-decision-4b":0.799028310455341,"open/robojev-27b-v1@0.5":0.9931031523193579,"open/robojev-27b":null,"open/robojev-4b-v2":0.9738159388803848,"open/robojev-4b-v3@0.25":0.970687747001648,"open/robojev-4b-v3@0.5":0.9507586388020023,"open/robojev-4b-v3@0.75":0.8704295270205443,"open/robojev-4b-v3":0.7267629994168858,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.9499032400904243,"respan/span-02":0.92110103,"typesafe/jev-1.13":0.77,"JEV-27B-VL (10 frames)":0.9619585435829173,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.158203125}},{"suite":"unseen","id":"rbm-ood/mit_franka/45e39a64-fc77-4650-844d-8a2d82dc934d","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"45e39a64-fc77-4650-844d-8a2d82dc934d","predictions":{"RoboJev-27B":0.6337645031756989,"GPT-6 Astra":0.24,"GPT-6.1 Sol":0.64,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.45,"JEV-27B-VL":0.3791446580869453,"TypeSafe Jev 1.14":0.22,"Perplexity Decider":0.32890138467948304,"Liquid D1":0.6791786861878392,"Mercury Decide":0.29421496597446145,"Cloudflare Clef":0.3726,"cloudflare/clef-flash":0.4705,"cloudflare/clef-omni":0.2727,"liquid/d1-ultra":0.3337871508067881,"open/intern-decision-4b":0.43758935794935333,"open/robojev-27b-v1@0.5":0.4052453399870199,"open/robojev-27b":null,"open/robojev-4b-v2":0.6513548711105848,"open/robojev-4b-v3@0.25":0.7310585379600525,"open/robojev-4b-v3@0.5":0.6587873175270851,"open/robojev-4b-v3@0.75":0.3419172570227415,"open/robojev-4b-v3":0.2322495721973338,"openai/gpt-6-luna-decisions":0.24,"perplexity/pplx-decider-flash-v1.2":0.5570943251015017,"respan/span-02":0.5410342,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.45680827140048674,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0260009765625}},{"suite":"unseen","id":"rbm-ood/mit_franka/46e9bca6-7817-43fb-914b-edcc12e8010a","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"46e9bca6-7817-43fb-914b-edcc12e8010a","predictions":{"RoboJev-27B":0.04042581192018865,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.08350600672299434,"TypeSafe Jev 1.14":0.16,"Perplexity Decider":0.09975020650715868,"Liquid D1":0.29421497216298875,"Mercury Decide":0.01098694163883665,"Cloudflare Clef":0.1219,"cloudflare/clef-flash":0.3424,"cloudflare/clef-omni":0.2313,"liquid/d1-ultra":0.10691173965049809,"open/intern-decision-4b":0.36247442200877295,"open/robojev-27b-v1@0.5":0.016017565021327423,"open/robojev-27b":null,"open/robojev-4b-v2":0.0032876614041202805,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.013703364243695216,"open/robojev-4b-v3@0.75":0.011381877728436919,"open/robojev-4b-v3":0.01146957225399579,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.16697895967729895,"respan/span-02":0.5360721,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.12747655525591656,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.138671875}},{"suite":"unseen","id":"rbm-ood/mit_franka/48279aac-ff7f-462d-9a1d-9ab718f8c2dd","task":"Pick up the spatula and stir the beans in the pot","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"48279aac-ff7f-462d-9a1d-9ab718f8c2dd","predictions":{"RoboJev-27B":0.5429610773476538,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.2809183212139465,"TypeSafe Jev 1.14":0.13,"Perplexity Decider":0.43372051521810606,"Liquid D1":0.5312093733737563,"Mercury Decide":0.24508502416032488,"Cloudflare Clef":0.3049,"cloudflare/clef-flash":0.5237,"cloudflare/clef-omni":0.2564,"liquid/d1-ultra":0.5,"open/intern-decision-4b":0.5,"open/robojev-27b-v1@0.5":0.2193944853323342,"open/robojev-27b":null,"open/robojev-4b-v2":0.2905205683918636,"open/robojev-4b-v3@0.25":0.531209409236908,"open/robojev-4b-v3@0.5":0.2847434534005251,"open/robojev-4b-v3@0.75":0.27840626377504696,"open/robojev-4b-v3":0.31845749647192534,"openai/gpt-6-luna-decisions":0.1,"perplexity/pplx-decider-flash-v1.2":0.13562256480626494,"respan/span-02":0.8191958,"typesafe/jev-1.13":0.19,"JEV-27B-VL (10 frames)":0.3809627117817221,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.012451171875}},{"suite":"unseen","id":"rbm-ood/mit_franka/4841ae7f-51c0-44d1-981c-7e22b1765ecb","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"4841ae7f-51c0-44d1-981c-7e22b1765ecb","predictions":{"RoboJev-27B":0.8769704731926623,"GPT-6 Astra":0.93,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8024335689185014,"TypeSafe Jev 1.14":0.78,"Perplexity Decider":0.8972111671953094,"Liquid D1":0.9046505415276079,"Mercury Decide":0.9740426444975988,"Cloudflare Clef":0.575,"cloudflare/clef-flash":0.6931,"cloudflare/clef-omni":0.5171,"liquid/d1-ultra":0.7658012615387644,"open/intern-decision-4b":0.5777854893190272,"open/robojev-27b-v1@0.5":0.9627363847026904,"open/robojev-27b":null,"open/robojev-4b-v2":0.05206535942424779,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.8848796562508825,"open/robojev-4b-v3@0.75":0.6713474489845783,"open/robojev-4b-v3":0.3548412084498786,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.8155876164220847,"respan/span-02":0.82663774,"typesafe/jev-1.13":0.78,"JEV-27B-VL (10 frames)":0.8655010063177881,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.11279296875}},{"suite":"unseen","id":"rbm-ood/mit_franka/48ae3c66-1ca7-4dfa-91ef-0abb06817d2c","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"48ae3c66-1ca7-4dfa-91ef-0abb06817d2c","predictions":{"RoboJev-27B":0.0257021027164817,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.07,"JEV-27B-VL":0.04621112298967851,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.04999977563273952,"Liquid D1":0.02931222905542399,"Mercury Decide":0.012431652213825342,"Cloudflare Clef":0.0622,"cloudflare/clef-flash":0.2501,"cloudflare/clef-omni":0.1441,"liquid/d1-ultra":0.0491779544813567,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.0025547741674945834,"open/robojev-27b":null,"open/robojev-4b-v2":0.002751490629587489,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.007144725422878838,"open/robojev-4b-v3@0.75":0.006692850722353873,"open/robojev-4b-v3":0.0053922199218183735,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.07885776218096323,"respan/span-02":0.076914296,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.04618032463342127,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0128173828125}},{"suite":"unseen","id":"rbm-ood/mit_franka/49163975-14fa-4df9-b022-361889a59960","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"49163975-14fa-4df9-b022-361889a59960","predictions":{"RoboJev-27B":0.2780082979518143,"GPT-6 Astra":0.16,"GPT-6.1 Sol":0.17,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.2138425744769906,"TypeSafe Jev 1.14":0.23,"Perplexity Decider":0.0887184648113899,"Liquid D1":0.6513548646660542,"Mercury Decide":0.06754668926255561,"Cloudflare Clef":0.2056,"cloudflare/clef-flash":0.2779,"cloudflare/clef-omni":0.1595,"liquid/d1-ultra":0.3560898041822152,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.03276530435621701,"open/robojev-27b":null,"open/robojev-4b-v2":0.20762754743879291,"open/robojev-4b-v3@0.25":0.13296423852443695,"open/robojev-4b-v3@0.5":0.0671334948723516,"open/robojev-4b-v3@0.75":0.03648068840213454,"open/robojev-4b-v3":0.020659669708358676,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.4320224367005386,"respan/span-02":0.35757673,"typesafe/jev-1.13":0.3,"JEV-27B-VL (10 frames)":0.2607772498676964,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.056640625}},{"suite":"unseen","id":"rbm-ood/mit_franka/49c291d4-ca32-43b0-ab1d-18971e1cc5ba","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"49c291d4-ca32-43b0-ab1d-18971e1cc5ba","predictions":{"RoboJev-27B":0.1749256706458336,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.06,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.2596588339550889,"TypeSafe Jev 1.14":0.23,"Perplexity Decider":0.154735706081083,"Liquid D1":0.7057850154599563,"Mercury Decide":0.07585817897661679,"Cloudflare Clef":0.4639,"cloudflare/clef-flash":0.6004,"cloudflare/clef-omni":0.3919,"liquid/d1-ultra":0.3229012912817457,"open/intern-decision-4b":0.39193998888916504,"open/robojev-27b-v1@0.5":0.1288053613728154,"open/robojev-27b":null,"open/robojev-4b-v2":0.010419816599485524,"open/robojev-4b-v3@0.25":0.3486451506614685,"open/robojev-4b-v3@0.5":0.10858632498619036,"open/robojev-4b-v3@0.75":0.04330410454906981,"open/robojev-4b-v3":0.03693826366802302,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.5647219146474535,"respan/span-02":0.7726406,"typesafe/jev-1.13":0.33,"JEV-27B-VL (10 frames)":0.18736559478804865,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0240478515625}},{"suite":"unseen","id":"rbm-ood/mit_franka/4a81a138-b2ea-43e1-8a1c-1fc7497dbe3f","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"4a81a138-b2ea-43e1-8a1c-1fc7497dbe3f","predictions":{"RoboJev-27B":0.4500112779190627,"GPT-6 Astra":0.18,"GPT-6.1 Sol":0.15,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.6315615372220431,"TypeSafe Jev 1.14":0.28,"Perplexity Decider":0.7381209302760416,"Liquid D1":0.9859363713038174,"Mercury Decide":0.5621765008857981,"Cloudflare Clef":0.6157,"cloudflare/clef-flash":0.6891,"cloudflare/clef-omni":0.1373,"liquid/d1-ultra":0.4507950784795865,"open/intern-decision-4b":0.799028310455341,"open/robojev-27b-v1@0.5":0.23924020717825403,"open/robojev-27b":null,"open/robojev-4b-v2":0.008352675304716173,"open/robojev-4b-v3@0.25":0.8807970285415649,"open/robojev-4b-v3@0.5":0.1709446101989739,"open/robojev-4b-v3@0.75":0.09432751595727837,"open/robojev-4b-v3":0.053129261209546814,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.6512636825136311,"respan/span-02":0.5792421,"typesafe/jev-1.13":0.34,"JEV-27B-VL (10 frames)":0.6097986243055264,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00628662109375}},{"suite":"unseen","id":"rbm-ood/mit_franka/4c9422ed-3f72-4eb6-a7eb-feea7c18e696","task":"Pull a tissue from the tissue box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"4c9422ed-3f72-4eb6-a7eb-feea7c18e696","predictions":{"RoboJev-27B":0.5263745927038098,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.31804752376898027,"TypeSafe Jev 1.14":0.49,"Perplexity Decider":0.4533426759264571,"Liquid D1":0.867035763237924,"Mercury Decide":0.4073334000459302,"Cloudflare Clef":0.4541,"cloudflare/clef-flash":0.487,"cloudflare/clef-omni":0.6846,"liquid/d1-ultra":0.6439101958177847,"open/intern-decision-4b":0.4686721718608801,"open/robojev-27b-v1@0.5":0.35548770912145305,"open/robojev-27b":null,"open/robojev-4b-v2":0.9456867326137218,"open/robojev-4b-v3@0.25":0.8175744414329529,"open/robojev-4b-v3@0.5":0.5974224658882353,"open/robojev-4b-v3@0.75":0.38315208923909133,"open/robojev-4b-v3":0.2841612815794545,"openai/gpt-6-luna-decisions":0.13,"perplexity/pplx-decider-flash-v1.2":0.5791535736803207,"respan/span-02":0.79414934,"typesafe/jev-1.13":0.53,"JEV-27B-VL (10 frames)":0.4879689024844396,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0791015625}},{"suite":"unseen","id":"rbm-ood/mit_franka/4d30a0de-bd76-43fb-ab53-42548d043162","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"4d30a0de-bd76-43fb-ab53-42548d043162","predictions":{"RoboJev-27B":0.2659434830529177,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.0596564514973722,"TypeSafe Jev 1.14":0.33,"Perplexity Decider":0.06925931386610742,"Liquid D1":0.9149009607937928,"Mercury Decide":0.025957355219835308,"Cloudflare Clef":0.4629,"cloudflare/clef-flash":0.286,"cloudflare/clef-omni":0.5111,"liquid/d1-ultra":0.12189697789365844,"open/intern-decision-4b":0.34810523633137336,"open/robojev-27b-v1@0.5":0.04495683770286962,"open/robojev-27b":null,"open/robojev-4b-v2":0.01138187822152329,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.12199371684192196,"open/robojev-4b-v3@0.75":0.13643297762397494,"open/robojev-4b-v3":0.1792055554427502,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.4892475495599296,"respan/span-02":0.26309618,"typesafe/jev-1.13":0.6,"JEV-27B-VL (10 frames)":0.11360988177285238,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1142578125}},{"suite":"unseen","id":"rbm-ood/mit_franka/4dd57b74-112b-4241-b941-e1530d3d93b9","task":"Pick up the spoon and place it inside the cup","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"4dd57b74-112b-4241-b941-e1530d3d93b9","predictions":{"RoboJev-27B":0.0030040674702504445,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.00912963793671665,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.012556000673722983,"Liquid D1":0.29421497216298875,"Mercury Decide":0.001810210740120113,"Cloudflare Clef":0.1982,"cloudflare/clef-flash":0.2832,"cloudflare/clef-omni":0.1621,"liquid/d1-ultra":0.10228896111898701,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.0005562779620787441,"open/robojev-27b":null,"open/robojev-4b-v2":0.0012900470555811355,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.017755273617510888,"open/robojev-4b-v3@0.75":0.008992055872561407,"open/robojev-4b-v3":0.009249319533522623,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2927639025116816,"respan/span-02":0.8235841,"typesafe/jev-1.13":0.15,"JEV-27B-VL (10 frames)":0.009107309075071807,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0033721923828125}},{"suite":"unseen","id":"rbm-ood/mit_franka/519d5f5d-7b81-4b7f-9134-d14af6922ab3","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"519d5f5d-7b81-4b7f-9134-d14af6922ab3","predictions":{"RoboJev-27B":0.41085266996804537,"GPT-6 Astra":0.73,"GPT-6.1 Sol":0.16,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.2479901091861985,"TypeSafe Jev 1.14":0.53,"Perplexity Decider":0.25994569589749766,"Liquid D1":0.8670357615200474,"Mercury Decide":0.22270013366638422,"Cloudflare Clef":0.2501,"cloudflare/clef-flash":0.4137,"cloudflare/clef-omni":0.1699,"liquid/d1-ultra":0.5369560013004135,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.2308763174564744,"open/robojev-27b":null,"open/robojev-4b-v2":0.9272127908057297,"open/robojev-4b-v3@0.25":0.8354835510253906,"open/robojev-4b-v3@0.5":0.8381784546520696,"open/robojev-4b-v3@0.75":0.777299857680221,"open/robojev-4b-v3":0.7478081785025862,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.5910994134321176,"respan/span-02":0.27406973,"typesafe/jev-1.13":0.47,"JEV-27B-VL (10 frames)":0.2741296409820395,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2392578125}},{"suite":"unseen","id":"rbm-ood/mit_franka/5293dca8-22bd-49e0-bf4a-014b4a87fc42","task":"Pull a tissue from the tissue box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"5293dca8-22bd-49e0-bf4a-014b4a87fc42","predictions":{"RoboJev-27B":0.11771832036904609,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.05310691236624052,"TypeSafe Jev 1.14":0.11,"Perplexity Decider":0.07520674251981982,"Liquid D1":0.3775406828054583,"Mercury Decide":0.0159063879797589,"Cloudflare Clef":0.3357,"cloudflare/clef-flash":0.2403,"cloudflare/clef-omni":0.3591,"liquid/d1-ultra":0.26179523991529324,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.0013683498807546823,"open/robojev-27b":null,"open/robojev-4b-v2":0.6713474383467429,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.014621593697422728,"open/robojev-4b-v3@0.75":0.008992055872561407,"open/robojev-4b-v3":0.006692851401910932,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.34892824769341196,"respan/span-02":0.89550555,"typesafe/jev-1.13":0.09,"JEV-27B-VL (10 frames)":0.10182415155641485,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0128173828125}},{"suite":"unseen","id":"rbm-ood/mit_franka/52b30f87-5541-4d97-976c-f1083c06764d","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"52b30f87-5541-4d97-976c-f1083c06764d","predictions":{"RoboJev-27B":0.010876689765159887,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.012196053968030005,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.034051880836857645,"Liquid D1":0.0850990519679964,"Mercury Decide":0.0033766119304295844,"Cloudflare Clef":0.1183,"cloudflare/clef-flash":0.3381,"cloudflare/clef-omni":0.224,"liquid/d1-ultra":0.08552782088472596,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.002666037621288115,"open/robojev-27b":null,"open/robojev-4b-v2":0.002751490629587489,"open/robojev-4b-v3@0.25":0.009708477184176445,"open/robojev-4b-v3@0.5":0.004233320503182646,"open/robojev-4b-v3@0.75":0.0030982660175204184,"open/robojev-4b-v3":0.002816147667248498,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.035187315777170575,"respan/span-02":0.124723084,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.015810856021948684,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00102996826171875}},{"suite":"unseen","id":"rbm-ood/mit_franka/538df936-e738-4213-a454-c48cfd0ddff5","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"538df936-e738-4213-a454-c48cfd0ddff5","predictions":{"RoboJev-27B":0.8276580393785987,"GPT-6 Astra":0.25,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.8888820687686355,"TypeSafe Jev 1.14":0.76,"Perplexity Decider":0.9072525346330245,"Liquid D1":0.9669140236373025,"Mercury Decide":0.9770226297972673,"Cloudflare Clef":0.5731,"cloudflare/clef-flash":0.7325,"cloudflare/clef-omni":0.7491,"liquid/d1-ultra":0.8613434764947244,"open/intern-decision-4b":0.8815938286018441,"open/robojev-27b-v1@0.5":0.9550003407847745,"open/robojev-27b":null,"open/robojev-4b-v2":0.14359896340218653,"open/robojev-4b-v3@0.25":0.977022647857666,"open/robojev-4b-v3@0.5":0.7992444628236429,"open/robojev-4b-v3@0.75":0.23317378360550628,"open/robojev-4b-v3":0.1637708093883215,"openai/gpt-6-luna-decisions":0.99,"perplexity/pplx-decider-flash-v1.2":0.9341778211676534,"respan/span-02":0.90493226,"typesafe/jev-1.13":0.77,"JEV-27B-VL (10 frames)":0.8970565398338732,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0057373046875}},{"suite":"unseen","id":"rbm-ood/mit_franka/55b8baa3-0054-4abe-acba-b3c66577d4fd","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"55b8baa3-0054-4abe-acba-b3c66577d4fd","predictions":{"RoboJev-27B":0.5794415507084549,"GPT-6 Astra":0.18,"GPT-6.1 Sol":0.25,"Claude Opus 5.5":0.66,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.3611900230638863,"TypeSafe Jev 1.14":0.25,"Perplexity Decider":0.40771010954189757,"Liquid D1":0.7057850278370112,"Mercury Decide":0.3208212878370535,"Cloudflare Clef":0.57,"cloudflare/clef-flash":0.4578,"cloudflare/clef-omni":0.4173,"liquid/d1-ultra":0.620965177756194,"open/intern-decision-4b":0.37709365395745764,"open/robojev-27b-v1@0.5":0.9072200042864493,"open/robojev-27b":null,"open/robojev-4b-v2":0.06424971190493048,"open/robojev-4b-v3@0.25":0.9525741338729858,"open/robojev-4b-v3@0.5":0.9810602019558173,"open/robojev-4b-v3@0.75":0.9741927167604716,"open/robojev-4b-v3":0.9380451002706788,"openai/gpt-6-luna-decisions":0.9,"perplexity/pplx-decider-flash-v1.2":0.6685977994216455,"respan/span-02":0.8760124,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.177388289531535,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.09423828125}},{"suite":"unseen","id":"rbm-ood/mit_franka/566afd80-feca-456d-908f-31a64c3569c4","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"566afd80-feca-456d-908f-31a64c3569c4","predictions":{"RoboJev-27B":0.4766386230352735,"GPT-6 Astra":0.2,"GPT-6.1 Sol":0.78,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.7297500218609674,"TypeSafe Jev 1.14":0.65,"Perplexity Decider":0.7376720819398271,"Liquid D1":0.984093610737347,"Mercury Decide":0.679178699175393,"Cloudflare Clef":0.5806,"cloudflare/clef-flash":0.881,"cloudflare/clef-omni":0.1465,"liquid/d1-ultra":0.4386055185499857,"open/intern-decision-4b":0.7064759712765732,"open/robojev-27b-v1@0.5":0.5012008077661424,"open/robojev-27b":null,"open/robojev-4b-v2":0.26370774468711267,"open/robojev-4b-v3@0.25":0.957912266254425,"open/robojev-4b-v3@0.5":0.549182531250921,"open/robojev-4b-v3@0.75":0.15886909401879357,"open/robojev-4b-v3":0.05887058738679302,"openai/gpt-6-luna-decisions":0.53,"perplexity/pplx-decider-flash-v1.2":0.860096137013734,"respan/span-02":0.75285536,"typesafe/jev-1.13":0.64,"JEV-27B-VL (10 frames)":0.7298164426418119,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2177734375}},{"suite":"unseen","id":"rbm-ood/mit_franka/56e82482-c443-4336-8d1c-afed307ce817","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"56e82482-c443-4336-8d1c-afed307ce817","predictions":{"RoboJev-27B":0.0991633777719335,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.08,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.3367001538975672,"TypeSafe Jev 1.14":0.17,"Perplexity Decider":0.2866010474476278,"Liquid D1":0.5621765008857981,"Mercury Decide":0.05340333450779175,"Cloudflare Clef":0.3854,"cloudflare/clef-flash":0.3042,"cloudflare/clef-omni":0.1454,"liquid/d1-ultra":0.6209651777561939,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.18539480551574034,"open/robojev-27b":null,"open/robojev-4b-v2":0.0023025598229782147,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.01560037702180545,"open/robojev-4b-v3@0.75":0.005946149584938689,"open/robojev-4b-v3":0.003138491707937668,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.12922937073197602,"respan/span-02":0.09157819,"typesafe/jev-1.13":0.27,"JEV-27B-VL (10 frames)":0.2607034887369262,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00193023681640625}},{"suite":"unseen","id":"rbm-ood/mit_franka/588e3fa8-039d-444b-bcf0-bd39cecd436c","task":"Pull a tissue from the tissue box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"588e3fa8-039d-444b-bcf0-bd39cecd436c","predictions":{"RoboJev-27B":0.5914982340432452,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.4653365410886739,"TypeSafe Jev 1.14":0.41,"Perplexity Decider":0.3588876271684399,"Liquid D1":0.8175744806385543,"Mercury Decide":0.29421497216298875,"Cloudflare Clef":0.522,"cloudflare/clef-flash":0.7395,"cloudflare/clef-omni":0.8708,"liquid/d1-ultra":0.414461257641393,"open/intern-decision-4b":0.5930110454411601,"open/robojev-27b-v1@0.5":0.6642290157582158,"open/robojev-27b":null,"open/robojev-4b-v2":0.7614624931929147,"open/robojev-4b-v3@0.25":0.8933094143867493,"open/robojev-4b-v3@0.5":0.8914136750138096,"open/robojev-4b-v3@0.75":0.8157922105403737,"open/robojev-4b-v3":0.7478081785025862,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.579945304486358,"respan/span-02":0.87296236,"typesafe/jev-1.13":0.41,"JEV-27B-VL (10 frames)":0.3435761633454073,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.010986328125}},{"suite":"unseen","id":"rbm-ood/mit_franka/58c49e06-a5b9-4165-9178-d838dbb837b8","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"58c49e06-a5b9-4165-9178-d838dbb837b8","predictions":{"RoboJev-27B":0.6665277517248114,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.12,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.6545389153621747,"TypeSafe Jev 1.14":0.75,"Perplexity Decider":0.6579132818457505,"Liquid D1":0.9399133464597458,"Mercury Decide":0.6513548782017746,"Cloudflare Clef":0.3166,"cloudflare/clef-flash":0.548,"cloudflare/clef-omni":0.3845,"liquid/d1-ultra":0.6439101850233137,"open/intern-decision-4b":0.767101934678807,"open/robojev-27b-v1@0.5":0.7389944051507147,"open/robojev-27b":null,"open/robojev-4b-v2":0.006124677327180011,"open/robojev-4b-v3@0.25":0.8670357465744019,"open/robojev-4b-v3@0.5":0.22270012535630726,"open/robojev-4b-v3@0.75":0.14359896906129718,"open/robojev-4b-v3":0.09724120311457327,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.7772400944703197,"respan/span-02":0.92007875,"typesafe/jev-1.13":0.81,"JEV-27B-VL (10 frames)":0.774908336094828,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2353515625}},{"suite":"unseen","id":"rbm-ood/mit_franka/5920cd7a-c2b3-47ab-bc88-79b18e1024fb","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"5920cd7a-c2b3-47ab-bc88-79b18e1024fb","predictions":{"RoboJev-27B":0.055230664608225316,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.04047078698861515,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.02992450041715687,"Liquid D1":0.798186768138228,"Mercury Decide":0.025957360023456458,"Cloudflare Clef":0.3103,"cloudflare/clef-flash":0.4792,"cloudflare/clef-omni":0.4592,"liquid/d1-ultra":0.2341987426829336,"open/intern-decision-4b":0.5777854893190272,"open/robojev-27b-v1@0.5":0.04234371125201111,"open/robojev-27b":null,"open/robojev-4b-v2":0.008730681628235537,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.0671334948723516,"open/robojev-4b-v3@0.75":0.04330410454906981,"open/robojev-4b-v3":0.047919347698515906,"openai/gpt-6-luna-decisions":0.09,"perplexity/pplx-decider-flash-v1.2":0.2802778578788128,"respan/span-02":0.8425203,"typesafe/jev-1.13":0.41,"JEV-27B-VL (10 frames)":0.031033031520557683,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00860595703125}},{"suite":"unseen","id":"rbm-ood/mit_franka/5a977a2c-6b2d-4c3d-9266-44c66d77f666","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"5a977a2c-6b2d-4c3d-9266-44c66d77f666","predictions":{"RoboJev-27B":0.04954607102795786,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.013260100215954751,"TypeSafe Jev 1.14":0.22,"Perplexity Decider":0.04832742907285361,"Liquid D1":0.21206881431678096,"Mercury Decide":0.007577243004700326,"Cloudflare Clef":0.4242,"cloudflare/clef-flash":0.4156,"cloudflare/clef-omni":0.4245,"liquid/d1-ultra":0.21695809590771967,"open/intern-decision-4b":0.34810523633137336,"open/robojev-27b-v1@0.5":0.0015477324165649076,"open/robojev-27b":null,"open/robojev-4b-v2":0.018465477873242233,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.0671334948723516,"open/robojev-4b-v3@0.75":0.08463674788192488,"open/robojev-4b-v3":0.12384396710192513,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.2129970920411027,"respan/span-02":0.28261402,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.02825642832872592,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0032806396484375}},{"suite":"unseen","id":"rbm-ood/mit_franka/5aa9a854-1ba8-48d2-94b6-0926f5f8fc5a","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"5aa9a854-1ba8-48d2-94b6-0926f5f8fc5a","predictions":{"RoboJev-27B":0.5299237430492417,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.5114923464183581,"TypeSafe Jev 1.14":0.43,"Perplexity Decider":0.37990889866369326,"Liquid D1":0.7981867873410141,"Mercury Decide":0.6224593312018546,"Cloudflare Clef":0.4233,"cloudflare/clef-flash":0.5503,"cloudflare/clef-omni":0.527,"liquid/d1-ultra":0.7830419080912434,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.30089693855915445,"open/robojev-27b":null,"open/robojev-4b-v2":0.0022022489536237186,"open/robojev-4b-v3@0.25":0.18242551386356354,"open/robojev-4b-v3@0.5":0.03828411009766295,"open/robojev-4b-v3@0.75":0.02580728323952834,"open/robojev-4b-v3":0.01499717745111633,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.6807635990430049,"respan/span-02":0.19797616,"typesafe/jev-1.13":0.59,"JEV-27B-VL (10 frames)":0.5141319795654968,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.06298828125}},{"suite":"unseen","id":"rbm-ood/mit_franka/5b261f71-de3a-4626-bb12-6aa2f69af2f0","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"5b261f71-de3a-4626-bb12-6aa2f69af2f0","predictions":{"RoboJev-27B":0.008684271425548317,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.03074364713690206,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.04260890275410695,"Liquid D1":0.16451646699291617,"Mercury Decide":0.02595735974089048,"Cloudflare Clef":0.2402,"cloudflare/clef-flash":0.2445,"cloudflare/clef-omni":0.1185,"liquid/d1-ultra":0.07811526640606889,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.0012617146859881276,"open/robojev-27b":null,"open/robojev-4b-v2":0.04032423126830159,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.03828411009766295,"open/robojev-4b-v3@0.75":0.028975397327291364,"open/robojev-4b-v3":0.025548296110078653,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.12220469874328259,"respan/span-02":0.058254004,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.019290442352925267,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00347900390625}},{"suite":"unseen","id":"rbm-ood/mit_franka/5dba8377-0c73-48c0-89f2-85e16fee39bd","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"5dba8377-0c73-48c0-89f2-85e16fee39bd","predictions":{"RoboJev-27B":0.8444927514246934,"GPT-6 Astra":0.77,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.6527952390029181,"TypeSafe Jev 1.14":0.4,"Perplexity Decider":0.729363560481975,"Liquid D1":0.8807970654616711,"Mercury Decide":0.9324533055754921,"Cloudflare Clef":0.4441,"cloudflare/clef-flash":0.8545,"cloudflare/clef-omni":0.8615,"liquid/d1-ultra":0.7382047555356107,"open/intern-decision-4b":0.7318060856600669,"open/robojev-27b-v1@0.5":0.9211333637763175,"open/robojev-27b":null,"open/robojev-4b-v2":0.06161735137356937,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.9507586388020023,"open/robojev-4b-v3@0.75":0.8489244915244398,"open/robojev-4b-v3":0.7579190349557637,"openai/gpt-6-luna-decisions":0.66,"perplexity/pplx-decider-flash-v1.2":0.6180389032169886,"respan/span-02":0.93448234,"typesafe/jev-1.13":0.31,"JEV-27B-VL (10 frames)":0.7965790752930803,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.51953125}},{"suite":"unseen","id":"rbm-ood/mit_franka/5e674c40-7e9b-4263-9a97-f7cdf3652ff6","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"5e674c40-7e9b-4263-9a97-f7cdf3652ff6","predictions":{"RoboJev-27B":0.269162008969439,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":0.29834604757917593,"TypeSafe Jev 1.14":0.22,"Perplexity Decider":0.24633543498604665,"Liquid D1":0.1824255415859996,"Mercury Decide":0.03308598041471092,"Cloudflare Clef":0.3587,"cloudflare/clef-flash":0.3764,"cloudflare/clef-omni":0.1729,"liquid/d1-ultra":0.35608980418221525,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.047723064614138076,"open/robojev-27b":null,"open/robojev-4b-v2":0.003757049695787553,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.011276606158891207,"open/robojev-4b-v3@0.75":0.010731211960485985,"open/robojev-4b-v3":0.007064018099624773,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.37441914436934004,"respan/span-02":0.17395109,"typesafe/jev-1.13":0.13,"JEV-27B-VL (10 frames)":0.3572621735945632,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00225830078125}},{"suite":"unseen","id":"rbm-ood/mit_franka/5f4ce0ee-ac41-4d54-bb09-903f1153c78c","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"5f4ce0ee-ac41-4d54-bb09-903f1153c78c","predictions":{"RoboJev-27B":0.23942568407719617,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.5076426485640868,"TypeSafe Jev 1.14":0.48,"Perplexity Decider":0.31822314988308925,"Liquid D1":0.8519528057272543,"Mercury Decide":0.37754066879814546,"Cloudflare Clef":0.3345,"cloudflare/clef-flash":0.558,"cloudflare/clef-omni":0.326,"liquid/d1-ultra":0.6877959283347255,"open/intern-decision-4b":0.36247442200877295,"open/robojev-27b-v1@0.5":0.2442688226632891,"open/robojev-27b":null,"open/robojev-4b-v2":0.0032876614041202805,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.04078132817181798,"open/robojev-4b-v3@0.75":0.0171641516746209,"open/robojev-4b-v3":0.010300413398065098,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.4691114880368214,"respan/span-02":0.087103955,"typesafe/jev-1.13":0.35,"JEV-27B-VL (10 frames)":0.41765293954445365,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.07470703125}},{"suite":"unseen","id":"rbm-ood/mit_franka/60dd34a2-a44b-4f7b-b97a-9189ec164365","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"60dd34a2-a44b-4f7b-b97a-9189ec164365","predictions":{"RoboJev-27B":0.09425692436312443,"GPT-6 Astra":0.86,"GPT-6.1 Sol":0.85,"Claude Opus 5.5":0.75,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.0636659372381661,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.1096837468428875,"Liquid D1":0.3486451217982255,"Mercury Decide":0.014063626914109765,"Cloudflare Clef":0.1566,"cloudflare/clef-flash":0.1879,"cloudflare/clef-omni":0.4011,"liquid/d1-ultra":0.39072106197134493,"open/intern-decision-4b":0.4686721718608801,"open/robojev-27b-v1@0.5":0.04759237435928629,"open/robojev-27b":null,"open/robojev-4b-v2":0.004905405551811006,"open/robojev-4b-v3@0.25":0.29421496391296387,"open/robojev-4b-v3@0.5":0.1804712758005596,"open/robojev-4b-v3@0.75":0.09953688489563063,"open/robojev-4b-v3":0.03326028532667912,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.17310370619671664,"respan/span-02":0.67609626,"typesafe/jev-1.13":0.15,"JEV-27B-VL (10 frames)":0.09687034229964309,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.07373046875}},{"suite":"unseen","id":"rbm-ood/mit_franka/648758dd-b8fb-4aa0-bb5a-286d1d89aadb","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"648758dd-b8fb-4aa0-bb5a-286d1d89aadb","predictions":{"RoboJev-27B":0.2316053482703571,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.2716782366848798,"TypeSafe Jev 1.14":0.17,"Perplexity Decider":0.28345595951998,"Liquid D1":0.880797068590724,"Mercury Decide":0.02931223234129297,"Cloudflare Clef":0.4245,"cloudflare/clef-flash":0.7425,"cloudflare/clef-omni":0.5016,"liquid/d1-ultra":0.15730750212730107,"open/intern-decision-4b":0.37709365395745764,"open/robojev-27b-v1@0.5":0.018734590150242907,"open/robojev-27b":null,"open/robojev-4b-v2":0.0034372413231743533,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.03828411009766295,"open/robojev-4b-v3@0.75":0.015267154896343218,"open/robojev-4b-v3":0.01146957225399579,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.4156266727237088,"respan/span-02":0.1841678,"typesafe/jev-1.13":0.44,"JEV-27B-VL (10 frames)":0.3387526913558334,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.46484375}},{"suite":"unseen","id":"rbm-ood/mit_franka/663b531c-43f0-4f96-af80-083bd06f827b","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"663b531c-43f0-4f96-af80-083bd06f827b","predictions":{"RoboJev-27B":0.7560457749062852,"GPT-6 Astra":0.2,"GPT-6.1 Sol":0.16,"Claude Opus 5.5":0.25,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.8574645477412487,"TypeSafe Jev 1.14":0.53,"Perplexity Decider":0.7669202039426465,"Liquid D1":0.9820137908274928,"Mercury Decide":0.9890130580373244,"Cloudflare Clef":0.677,"cloudflare/clef-flash":0.4492,"cloudflare/clef-omni":0.1308,"liquid/d1-ultra":0.414461257641393,"open/intern-decision-4b":0.7557061813028185,"open/robojev-27b-v1@0.5":0.8404908307783248,"open/robojev-27b":null,"open/robojev-4b-v2":0.006124677327180011,"open/robojev-4b-v3@0.25":0.8933094143867493,"open/robojev-4b-v3@0.5":0.5,"open/robojev-4b-v3@0.75":0.21256653766057104,"open/robojev-4b-v3":0.08810813794451551,"openai/gpt-6-luna-decisions":0.58,"perplexity/pplx-decider-flash-v1.2":0.8479284114144457,"respan/span-02":0.31529644,"typesafe/jev-1.13":0.55,"JEV-27B-VL (10 frames)":0.7179350671758163,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0306396484375}},{"suite":"unseen","id":"rbm-ood/mit_franka/6711b1bb-ebb5-4aff-b9c0-ecc4a37b9437","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"6711b1bb-ebb5-4aff-b9c0-ecc4a37b9437","predictions":{"RoboJev-27B":0.003108050632815227,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.0016479301150492739,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.02575320033996787,"Liquid D1":0.027585282626503727,"Mercury Decide":0.0009110511028480203,"Cloudflare Clef":0.2392,"cloudflare/clef-flash":0.1794,"cloudflare/clef-omni":0.0934,"liquid/d1-ultra":0.05400543770763665,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.000187192041411178,"open/robojev-27b":null,"open/robojev-4b-v2":0.0023025598229782147,"open/robojev-4b-v3@0.25":0.02595735713839531,"open/robojev-4b-v3@0.5":0.006269376036423619,"open/robojev-4b-v3@0.75":0.0032876613688676065,"open/robojev-4b-v3":0.0016373401530355304,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.0645291437554236,"respan/span-02":0.11309275,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.006813249088572495,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000911712646484375}},{"suite":"unseen","id":"rbm-ood/mit_franka/67ea3c81-d7e1-4ddb-840e-4f16e09a8da2","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"67ea3c81-d7e1-4ddb-840e-4f16e09a8da2","predictions":{"RoboJev-27B":0.07002934592740664,"GPT-6 Astra":0.83,"GPT-6.1 Sol":0.78,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.44813797437937264,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.24960404330968003,"Liquid D1":0.05665242052980391,"Mercury Decide":0.2018132270610754,"Cloudflare Clef":0.2094,"cloudflare/clef-flash":0.2671,"cloudflare/clef-omni":0.171,"liquid/d1-ultra":0.17794899285306523,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.24023519005717045,"open/robojev-27b":null,"open/robojev-4b-v2":0.004293165515526464,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.01203420913122135,"open/robojev-4b-v3@0.75":0.007100415903386552,"open/robojev-4b-v3":0.005108442412304043,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.11386040233903645,"respan/span-02":0.6435533,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.33451663044390445,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.003082275390625}},{"suite":"unseen","id":"rbm-ood/mit_franka/69bb936b-5edd-4ce4-b0ee-0b8014c39137","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"69bb936b-5edd-4ce4-b0ee-0b8014c39137","predictions":{"RoboJev-27B":0.03544804541638676,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.07,"JEV-27B-VL":0.0465517891800519,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.06264149316175117,"Liquid D1":0.256831980010821,"Mercury Decide":0.022977368488305953,"Cloudflare Clef":0.304,"cloudflare/clef-flash":0.2834,"cloudflare/clef-omni":0.0824,"liquid/d1-ultra":0.08946861361695119,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.02809996609888656,"open/robojev-27b":null,"open/robojev-4b-v2":0.03544887275269872,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.102380250911392,"open/robojev-4b-v3@0.75":0.08013780136639623,"open/robojev-4b-v3":0.06858087544025289,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.19725638107535864,"respan/span-02":0.22276156,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.030951141333826895,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0038299560546875}},{"suite":"unseen","id":"rbm-ood/mit_franka/6a94664c-7aa5-4936-9c88-40be9319a1b6","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"6a94664c-7aa5-4936-9c88-40be9319a1b6","predictions":{"RoboJev-27B":0.9490763654847203,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.65,"JEV-27B-VL":0.879419605089972,"TypeSafe Jev 1.14":0.71,"Perplexity Decider":0.828935698001782,"Liquid D1":0.8807970701552504,"Mercury Decide":0.9669140244715405,"Cloudflare Clef":0.2761,"cloudflare/clef-flash":0.2122,"cloudflare/clef-omni":0.079,"liquid/d1-ultra":0.9064276092007849,"open/intern-decision-4b":0.42221451068097277,"open/robojev-27b-v1@0.5":0.9292398180286687,"open/robojev-27b":null,"open/robojev-4b-v2":0.004488287139460313,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.8195287241994405,"open/robojev-4b-v3@0.75":0.7333927218765676,"open/robojev-4b-v3":0.3424998225293823,"openai/gpt-6-luna-decisions":0.9,"perplexity/pplx-decider-flash-v1.2":0.8817267348331268,"respan/span-02":0.158644,"typesafe/jev-1.13":0.82,"JEV-27B-VL (10 frames)":0.9078895643984776,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.65234375}},{"suite":"unseen","id":"rbm-ood/mit_franka/6a963be3-befc-454d-907a-d6634557e682","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"6a963be3-befc-454d-907a-d6634557e682","predictions":{"RoboJev-27B":0.0031200640710621484,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0013701831884825356,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.01156781207151116,"Liquid D1":0.03732688948593843,"Mercury Decide":0.0005884089171386213,"Cloudflare Clef":0.0557,"cloudflare/clef-flash":0.1539,"cloudflare/clef-omni":0.044,"liquid/d1-ultra":0.046920384893830484,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.00011827586990644885,"open/robojev-27b":null,"open/robojev-4b-v2":0.003593602817215226,"open/robojev-4b-v3@0.25":0.01098694372922182,"open/robojev-4b-v3@0.5":0.004233320503182646,"open/robojev-4b-v3@0.75":0.0029197498822566025,"open/robojev-4b-v3":0.0020341273969387797,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.025428915355325498,"respan/span-02":0.11948758,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.004144701826833503,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000644683837890625}},{"suite":"unseen","id":"rbm-ood/mit_franka/6b423129-f607-4ae2-8e84-4cf98ba5b7fa","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"6b423129-f607-4ae2-8e84-4cf98ba5b7fa","predictions":{"RoboJev-27B":0.6952651146618534,"GPT-6 Astra":0.78,"GPT-6.1 Sol":0.82,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.1491928821928311,"TypeSafe Jev 1.14":0.34,"Perplexity Decider":0.20425252562442528,"Liquid D1":0.5,"Mercury Decide":0.13296423676207594,"Cloudflare Clef":0.2242,"cloudflare/clef-flash":0.3347,"cloudflare/clef-omni":0.1602,"liquid/d1-ultra":0.24316814011226495,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.2518818288829614,"open/robojev-27b":null,"open/robojev-4b-v2":0.5555730307030312,"open/robojev-4b-v3@0.25":0.2689414322376251,"open/robojev-4b-v3@0.5":0.32658221149990796,"open/robojev-4b-v3@0.75":0.21256653766057104,"open/robojev-4b-v3":0.12384396710192513,"openai/gpt-6-luna-decisions":0.12,"perplexity/pplx-decider-flash-v1.2":0.45414092387292315,"respan/span-02":0.45305943,"typesafe/jev-1.13":0.39,"JEV-27B-VL (10 frames)":0.2909016199062252,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01068115234375}},{"suite":"unseen","id":"rbm-ood/mit_franka/6b5f3b7d-4869-455a-a689-432dceeca830","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"6b5f3b7d-4869-455a-a689-432dceeca830","predictions":{"RoboJev-27B":0.4627591371581297,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.35587583319537724,"TypeSafe Jev 1.14":0.48,"Perplexity Decider":0.32096521994478455,"Liquid D1":0.7310585786300049,"Mercury Decide":0.32082129433083023,"Cloudflare Clef":0.2115,"cloudflare/clef-flash":0.346,"cloudflare/clef-omni":0.1156,"liquid/d1-ultra":0.47533768343489957,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.4059249971726269,"open/robojev-27b":null,"open/robojev-4b-v2":0.7923724525612071,"open/robojev-4b-v3@0.25":0.4073334336280823,"open/robojev-4b-v3@0.5":0.6734177885000919,"open/robojev-4b-v3@0.75":0.756014627783845,"open/robojev-4b-v3":0.7579190349557637,"openai/gpt-6-luna-decisions":0.13,"perplexity/pplx-decider-flash-v1.2":0.310496098891154,"respan/span-02":0.21527018,"typesafe/jev-1.13":0.45,"JEV-27B-VL (10 frames)":0.47902263304938986,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2265625}},{"suite":"unseen","id":"rbm-ood/mit_franka/6c38f3c6-1258-4943-86bc-a84168201703","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"6c38f3c6-1258-4943-86bc-a84168201703","predictions":{"RoboJev-27B":0.8214077755894148,"GPT-6 Astra":0.2,"GPT-6.1 Sol":0.17,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.9084650597139149,"TypeSafe Jev 1.14":0.58,"Perplexity Decider":0.9229074286785542,"Liquid D1":0.9740426412009962,"Mercury Decide":0.9840936103583101,"Cloudflare Clef":0.6978,"cloudflare/clef-flash":0.4976,"cloudflare/clef-omni":0.5712,"liquid/d1-ultra":0.666212849193212,"open/intern-decision-4b":0.7193152314525416,"open/robojev-27b-v1@0.5":0.9382679931914771,"open/robojev-27b":null,"open/robojev-4b-v2":0.02297736939860946,"open/robojev-4b-v3@0.25":0.9740425944328308,"open/robojev-4b-v3@0.5":0.7152565465994749,"open/robojev-4b-v3@0.75":0.15886909401879357,"open/robojev-4b-v3":0.1125237519028778,"openai/gpt-6-luna-decisions":0.55,"perplexity/pplx-decider-flash-v1.2":0.9321220125910261,"respan/span-02":0.7370144,"typesafe/jev-1.13":0.85,"JEV-27B-VL (10 frames)":0.9006159895380551,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.52734375}},{"suite":"unseen","id":"rbm-ood/mit_franka/6d5c218b-66cd-4395-94c5-4024cde9f93c","task":"Pick up the spatula and stir the beans in the pot","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"6d5c218b-66cd-4395-94c5-4024cde9f93c","predictions":{"RoboJev-27B":0.7559452557347405,"GPT-6 Astra":0.93,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.47685078969522615,"TypeSafe Jev 1.14":0.34,"Perplexity Decider":0.4556134640080448,"Liquid D1":0.798186768138228,"Mercury Decide":0.7057850216484838,"Cloudflare Clef":0.4787,"cloudflare/clef-flash":0.5716,"cloudflare/clef-omni":0.1986,"liquid/d1-ultra":0.5,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.8552272957604706,"open/robojev-27b":null,"open/robojev-4b-v2":0.01138187822152329,"open/robojev-4b-v3@0.25":0.7310585379600525,"open/robojev-4b-v3@0.5":0.7772998746436928,"open/robojev-4b-v3@0.75":0.7668262163944938,"open/robojev-4b-v3":0.7579190349557637,"openai/gpt-6-luna-decisions":0.28,"perplexity/pplx-decider-flash-v1.2":0.47660034801034484,"respan/span-02":0.47273445,"typesafe/jev-1.13":0.31,"JEV-27B-VL (10 frames)":0.5463338322779997,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.037841796875}},{"suite":"unseen","id":"rbm-ood/mit_franka/6d6781e8-d812-4968-8e1f-8ae633df7341","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"6d6781e8-d812-4968-8e1f-8ae633df7341","predictions":{"RoboJev-27B":0.12737292681245327,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.06,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.09947418145601812,"TypeSafe Jev 1.14":0.17,"Perplexity Decider":0.1581182327052448,"Liquid D1":0.9149009480320036,"Mercury Decide":0.037326887879581695,"Cloudflare Clef":0.4196,"cloudflare/clef-flash":0.6133,"cloudflare/clef-omni":0.4204,"liquid/d1-ultra":0.18528536604722437,"open/intern-decision-4b":0.5624106420506467,"open/robojev-27b-v1@0.5":0.005978223529103922,"open/robojev-27b":null,"open/robojev-4b-v2":0.012431651137415392,"open/robojev-4b-v3@0.25":0.22270014882087708,"open/robojev-4b-v3@0.5":0.02612421708095358,"open/robojev-4b-v3@0.75":0.01011736424150334,"open/robojev-4b-v3":0.005691671058411752,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.4640336036851864,"respan/span-02":0.37697664,"typesafe/jev-1.13":0.17,"JEV-27B-VL (10 frames)":0.2564187932332935,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.008056640625}},{"suite":"unseen","id":"rbm-ood/mit_franka/70d81e02-e13b-40ca-ba35-0145cc226746","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"70d81e02-e13b-40ca-ba35-0145cc226746","predictions":{"RoboJev-27B":0.0025769739682808233,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.01802677381154407,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.026652222084976022,"Liquid D1":0.06371499958557338,"Mercury Decide":0.014063629961712851,"Cloudflare Clef":0.184,"cloudflare/clef-flash":0.2323,"cloudflare/clef-omni":0.0847,"liquid/d1-ultra":0.07129505923561442,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.0004833276752473058,"open/robojev-27b":null,"open/robojev-4b-v2":0.003927901641619978,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.009900079472737449,"open/robojev-4b-v3@0.75":0.007100415903386552,"open/robojev-4b-v3":0.006007651396687169,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.19597173110679603,"respan/span-02":0.17364645,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.011919990429119313,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00154876708984375}},{"suite":"unseen","id":"rbm-ood/mit_franka/70e1fe0f-2dc7-4813-b728-4f7b6f0dddb7","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"70e1fe0f-2dc7-4813-b728-4f7b6f0dddb7","predictions":{"RoboJev-27B":0.0343359997361006,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.0660006273354102,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.058336069451375094,"Liquid D1":0.01691491277114969,"Mercury Decide":0.022977370788146625,"Cloudflare Clef":0.1805,"cloudflare/clef-flash":0.1791,"cloudflare/clef-omni":0.1171,"liquid/d1-ultra":0.14465800616138325,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.010562529022522284,"open/robojev-27b":null,"open/robojev-4b-v2":0.004488287139460313,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.010566189227213266,"open/robojev-4b-v3@0.75":0.007990902377034759,"open/robojev-4b-v3":0.0053922199218183735,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.18230451119556082,"respan/span-02":0.6549039,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.07636989926961087,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.004913330078125}},{"suite":"unseen","id":"rbm-ood/mit_franka/741f8ab9-6d38-457e-95c9-4e52a1605535","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"741f8ab9-6d38-457e-95c9-4e52a1605535","predictions":{"RoboJev-27B":0.37906694902691357,"GPT-6 Astra":0.87,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.35,"JEV-27B-VL":0.3470977698579124,"TypeSafe Jev 1.14":0.44,"Perplexity Decider":0.3729199214262596,"Liquid D1":0.679178699175393,"Mercury Decide":0.4073334000459302,"Cloudflare Clef":0.3573,"cloudflare/clef-flash":0.4193,"cloudflare/clef-omni":0.2706,"liquid/d1-ultra":0.3229012912817457,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.6133788599143607,"open/robojev-27b":null,"open/robojev-4b-v2":0.3588504266804245,"open/robojev-4b-v3@0.25":0.622459352016449,"open/robojev-4b-v3@0.5":0.8195287241994405,"open/robojev-4b-v3@0.75":0.7972262276138262,"open/robojev-4b-v3":0.6932201840202893,"openai/gpt-6-luna-decisions":0.09,"perplexity/pplx-decider-flash-v1.2":0.3829568944262983,"respan/span-02":0.28104398,"typesafe/jev-1.13":0.51,"JEV-27B-VL (10 frames)":0.3325862873992134,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.08154296875}},{"suite":"unseen","id":"rbm-ood/mit_franka/74d78e31-da98-43c8-809a-0cdd6dbd337d","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"74d78e31-da98-43c8-809a-0cdd6dbd337d","predictions":{"RoboJev-27B":0.9727462768899269,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.9806953049456473,"TypeSafe Jev 1.14":0.9,"Perplexity Decider":0.993267362189587,"Liquid D1":0.994445075594701,"Mercury Decide":0.998674977526097,"Cloudflare Clef":0.903,"cloudflare/clef-flash":0.8811,"cloudflare/clef-omni":0.8918,"liquid/d1-ultra":0.9407227480104567,"open/intern-decision-4b":0.8998738837161642,"open/robojev-27b-v1@0.5":0.9939672894549436,"open/robojev-27b":null,"open/robojev-4b-v2":0.97894393279945,"open/robojev-4b-v3@0.25":0.9820137619972229,"open/robojev-4b-v3@0.5":0.9810602019558173,"open/robojev-4b-v3@0.75":0.9613683489514899,"open/robojev-4b-v3":0.9161618129189448,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9745330057963065,"respan/span-02":0.9411153,"typesafe/jev-1.13":0.85,"JEV-27B-VL (10 frames)":0.9756967383047133,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.59375}},{"suite":"unseen","id":"rbm-ood/mit_franka/7603a1bc-a20a-412c-92fa-76e4958ad58f","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"7603a1bc-a20a-412c-92fa-76e4958ad58f","predictions":{"RoboJev-27B":0.434517012629659,"GPT-6 Astra":0.78,"GPT-6.1 Sol":0.83,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.2840405567141976,"TypeSafe Jev 1.14":0.23,"Perplexity Decider":0.2774095096047522,"Liquid D1":0.679178699175393,"Mercury Decide":0.22270012850745968,"Cloudflare Clef":0.3319,"cloudflare/clef-flash":0.4498,"cloudflare/clef-omni":0.4874,"liquid/d1-ultra":0.26179524446438934,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.2024192877666109,"open/robojev-27b":null,"open/robojev-4b-v2":0.07585818098994364,"open/robojev-4b-v3@0.25":0.7549149990081787,"open/robojev-4b-v3@0.5":0.3561519473092389,"open/robojev-4b-v3@0.75":0.302940708044421,"open/robojev-4b-v3":0.1792055554427502,"openai/gpt-6-luna-decisions":0.11,"perplexity/pplx-decider-flash-v1.2":0.4665322796731717,"respan/span-02":0.20050083,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.2643965584465939,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00592041015625}},{"suite":"unseen","id":"rbm-ood/mit_franka/774e444f-681c-4602-9c1a-c87c59cb9e3f","task":"Pull a tissue from the tissue box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"774e444f-681c-4602-9c1a-c87c59cb9e3f","predictions":{"RoboJev-27B":0.3313508013878966,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.3974365301113748,"TypeSafe Jev 1.14":0.31,"Perplexity Decider":0.3618476628436785,"Liquid D1":0.46879062662624377,"Mercury Decide":0.2689414213699951,"Cloudflare Clef":0.3408,"cloudflare/clef-flash":0.4725,"cloudflare/clef-omni":0.2863,"liquid/d1-ultra":0.4507950668241079,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.5047098942217784,"open/robojev-27b":null,"open/robojev-4b-v2":0.2905205683918636,"open/robojev-4b-v3@0.25":0.6513549089431763,"open/robojev-4b-v3@0.5":0.7536956923154546,"open/robojev-4b-v3@0.75":0.7094794355493901,"open/robojev-4b-v3":0.5135836153966654,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.38291971168300704,"respan/span-02":0.15678225,"typesafe/jev-1.13":0.33,"JEV-27B-VL (10 frames)":0.29243181555470155,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01068115234375}},{"suite":"unseen","id":"rbm-ood/mit_franka/7a6d915b-9383-4c99-ac43-30b3e6ddb340","task":"Fold the towel in half","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"7a6d915b-9383-4c99-ac43-30b3e6ddb340","predictions":{"RoboJev-27B":0.004775162345361843,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.04293251726824757,"TypeSafe Jev 1.14":0.25,"Perplexity Decider":0.038247322727951186,"Liquid D1":0.3486451217982255,"Mercury Decide":0.005220126825239294,"Cloudflare Clef":0.1075,"cloudflare/clef-flash":0.2145,"cloudflare/clef-omni":0.0978,"liquid/d1-ultra":0.05153826937574945,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":0.0032407415750754583,"open/robojev-27b":null,"open/robojev-4b-v2":0.0893637337766288,"open/robojev-4b-v3@0.25":0.03308597952127457,"open/robojev-4b-v3@0.5":0.009900079472737449,"open/robojev-4b-v3@0.75":0.005282311488788821,"open/robojev-4b-v3":0.0036922283157701354,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.12264630256806712,"respan/span-02":0.22168322,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.021921623384023706,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.002471923828125}},{"suite":"unseen","id":"rbm-ood/mit_franka/7b458019-4662-457a-bc46-5615e9a1af17","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"7b458019-4662-457a-bc46-5615e9a1af17","predictions":{"RoboJev-27B":0.49858820151307826,"GPT-6 Astra":0.15,"GPT-6.1 Sol":0.24,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.6492955835296644,"TypeSafe Jev 1.14":0.54,"Perplexity Decider":0.7384182598991066,"Liquid D1":0.924141817889503,"Mercury Decide":0.8519528038477825,"Cloudflare Clef":0.6111,"cloudflare/clef-flash":0.868,"cloudflare/clef-omni":0.2026,"liquid/d1-ultra":0.39072108438586856,"open/intern-decision-4b":0.5777854893190272,"open/robojev-27b-v1@0.5":0.2969070398256867,"open/robojev-27b":null,"open/robojev-4b-v2":0.006692850868879798,"open/robojev-4b-v3@0.25":0.7981867790222168,"open/robojev-4b-v3@0.5":0.1804712758005596,"open/robojev-4b-v3@0.75":0.1295704729794557,"open/robojev-4b-v3":0.11806640532074496,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.7184807907557708,"respan/span-02":0.10322461,"typesafe/jev-1.13":0.31,"JEV-27B-VL (10 frames)":0.7445977070019413,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0260009765625}},{"suite":"unseen","id":"rbm-ood/mit_franka/7e4c9f98-39c1-4984-b86b-4f60d9eec5a5","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"7e4c9f98-39c1-4984-b86b-4f60d9eec5a5","predictions":{"RoboJev-27B":0.0022726621450749156,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.000371729754791497,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.010637886804078647,"Liquid D1":0.0169149115322077,"Mercury Decide":0.00027803087172176136,"Cloudflare Clef":0.1072,"cloudflare/clef-flash":0.1229,"cloudflare/clef-omni":0.1062,"liquid/d1-ultra":0.04269763397219835,"open/intern-decision-4b":0.10012611628383591,"open/robojev-27b-v1@0.5":0.00024629976659907313,"open/robojev-27b":null,"open/robojev-4b-v2":0.002631674205642126,"open/robojev-4b-v3@0.25":0.005911068990826607,"open/robojev-4b-v3@0.5":0.0030502597001447,"open/robojev-4b-v3@0.75":0.00244343308696661,"open/robojev-4b-v3":0.0020341273969387797,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.023924224910294927,"respan/span-02":0.08990679,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.0017940723174916615,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0007781982421875}},{"suite":"unseen","id":"rbm-ood/mit_franka/7f865ab8-c7c9-47f9-b7a9-a1dcf3bf5f41","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"7f865ab8-c7c9-47f9-b7a9-a1dcf3bf5f41","predictions":{"RoboJev-27B":0.00873070957737293,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.07835160049350365,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.06620746854699736,"Liquid D1":0.09009299396195182,"Mercury Decide":0.04742587267267827,"Cloudflare Clef":0.2137,"cloudflare/clef-flash":0.255,"cloudflare/clef-omni":0.1202,"liquid/d1-ultra":0.13865651085454228,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.0071902968053653695,"open/robojev-27b":null,"open/robojev-4b-v2":0.004106490957182719,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.010566189227213266,"open/robojev-4b-v3@0.75":0.007100415903386552,"open/robojev-4b-v3":0.0074556149068047885,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.24370817175312318,"respan/span-02":0.15581717,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.0379008996935631,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0023193359375}},{"suite":"unseen","id":"rbm-ood/mit_franka/815000fd-8761-4399-a7e3-c57e20f82bc5","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"815000fd-8761-4399-a7e3-c57e20f82bc5","predictions":{"RoboJev-27B":0.7559307155167918,"GPT-6 Astra":0.19,"GPT-6.1 Sol":0.79,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.5782409260382325,"TypeSafe Jev 1.14":0.61,"Perplexity Decider":0.4886934961526118,"Liquid D1":0.8354835371034369,"Mercury Decide":0.4378234991142019,"Cloudflare Clef":0.2402,"cloudflare/clef-flash":0.3421,"cloudflare/clef-omni":0.2765,"liquid/d1-ultra":0.5974659344706373,"open/intern-decision-4b":0.45308504361568214,"open/robojev-27b-v1@0.5":0.9298465613528383,"open/robojev-27b":null,"open/robojev-4b-v2":0.8720986012807731,"open/robojev-4b-v3@0.25":0.8670357465744019,"open/robojev-4b-v3@0.5":0.8195287241994405,"open/robojev-4b-v3@0.75":0.47027319113402044,"open/robojev-4b-v3":0.2953447966522927,"openai/gpt-6-luna-decisions":0.21,"perplexity/pplx-decider-flash-v1.2":0.5878867297402169,"respan/span-02":0.74937236,"typesafe/jev-1.13":0.54,"JEV-27B-VL (10 frames)":0.6503622486980859,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0140380859375}},{"suite":"unseen","id":"rbm-ood/mit_franka/83ccff35-571c-4a66-bf31-9d42097f5e1a","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"83ccff35-571c-4a66-bf31-9d42097f5e1a","predictions":{"RoboJev-27B":0.010866904373324765,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.020652191685415662,"TypeSafe Jev 1.14":0.11,"Perplexity Decider":0.043272683025844326,"Liquid D1":0.0026316742682230736,"Mercury Decide":0.00857748638785794,"Cloudflare Clef":0.0949,"cloudflare/clef-flash":0.1577,"cloudflare/clef-omni":0.0795,"liquid/d1-ultra":0.03531702388883135,"open/intern-decision-4b":0.1395062328236417,"open/robojev-27b-v1@0.5":0.012251365846026976,"open/robojev-27b":null,"open/robojev-4b-v2":0.0014746525778226533,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.008690106319066306,"open/robojev-4b-v3@0.75":0.01011736424150334,"open/robojev-4b-v3":0.01582154176925847,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.06893894240966336,"respan/span-02":0.074106686,"typesafe/jev-1.13":0.12,"JEV-27B-VL (10 frames)":0.0025921788860371743,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000732421875}},{"suite":"unseen","id":"rbm-ood/mit_franka/860f71b0-1e00-4d38-b2e3-42c68cece12c","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"860f71b0-1e00-4d38-b2e3-42c68cece12c","predictions":{"RoboJev-27B":0.020753389096654074,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.020496983139912776,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.0605893977709462,"Liquid D1":0.4378234844434674,"Mercury Decide":0.005220125301822759,"Cloudflare Clef":0.1615,"cloudflare/clef-flash":0.5738,"cloudflare/clef-omni":0.4082,"liquid/d1-ultra":0.06809489213509846,"open/intern-decision-4b":0.5624106420506467,"open/robojev-27b-v1@0.5":0.0012521626183072119,"open/robojev-27b":null,"open/robojev-4b-v2":0.006692850868879798,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.01560037702180545,"open/robojev-4b-v3@0.75":0.009538287541433899,"open/robojev-4b-v3":0.007868747659394765,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.08923439360439674,"respan/span-02":0.8951983,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.0294342446534788,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00628662109375}},{"suite":"unseen","id":"rbm-ood/mit_franka/86840c22-3271-4784-88d6-4484e219813f","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"86840c22-3271-4784-88d6-4484e219813f","predictions":{"RoboJev-27B":0.019122113682057188,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.0017864944238043837,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.024595316144931274,"Liquid D1":0.1561049013715009,"Mercury Decide":0.0014103584533336987,"Cloudflare Clef":0.1347,"cloudflare/clef-flash":0.3819,"cloudflare/clef-omni":0.1175,"liquid/d1-ultra":0.03367322854279349,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":3.677152184826175e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.0025170615300917137,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.0030982660175204184,"open/robojev-4b-v3":0.0018250014762326966,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.03752598444798428,"respan/span-02":0.1923132,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.057272525046284196,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0021820068359375}},{"suite":"unseen","id":"rbm-ood/mit_franka/86ad603d-87ca-4fc9-918d-347e28f9974d","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"86ad603d-87ca-4fc9-918d-347e28f9974d","predictions":{"RoboJev-27B":0.5029599983071465,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.07,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.7782041103343305,"TypeSafe Jev 1.14":0.74,"Perplexity Decider":0.8711534786357865,"Liquid D1":0.32082130082460697,"Mercury Decide":0.9669140192277585,"Cloudflare Clef":0.4712,"cloudflare/clef-flash":0.2905,"cloudflare/clef-omni":0.3621,"liquid/d1-ultra":0.6551469000827255,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.8809026149238803,"open/robojev-27b":null,"open/robojev-4b-v2":0.004293165515526464,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.09649050143553403,"open/robojev-4b-v3@0.75":0.054313266183183405,"open/robojev-4b-v3":0.03155642361885442,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.744778903104607,"respan/span-02":0.5499885,"typesafe/jev-1.13":0.78,"JEV-27B-VL (10 frames)":0.6274377457578658,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.30859375}},{"suite":"unseen","id":"rbm-ood/mit_franka/86bfc3b8-38bf-412b-8b9c-95bc73d0cc0c","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"86bfc3b8-38bf-412b-8b9c-95bc73d0cc0c","predictions":{"RoboJev-27B":0.14251723981353245,"GPT-6 Astra":0.06,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":0.3755253392702149,"TypeSafe Jev 1.14":0.5,"Perplexity Decider":0.20589400938053046,"Liquid D1":0.9149009642742806,"Mercury Decide":0.06008665648572012,"Cloudflare Clef":0.3846,"cloudflare/clef-flash":0.3138,"cloudflare/clef-omni":0.2134,"liquid/d1-ultra":0.6325127183904116,"open/intern-decision-4b":0.6932998143038492,"open/robojev-27b-v1@0.5":0.43858562848778787,"open/robojev-27b":null,"open/robojev-4b-v2":0.004293165515526464,"open/robojev-4b-v3@0.25":0.9046505093574524,"open/robojev-4b-v3@0.5":0.1368024864039654,"open/robojev-4b-v3@0.75":0.08013780136639623,"open/robojev-4b-v3":0.05593065484668503,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.7664259803189083,"respan/span-02":0.8231791,"typesafe/jev-1.13":0.63,"JEV-27B-VL (10 frames)":0.10754261642792554,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.56640625}},{"suite":"unseen","id":"rbm-ood/mit_franka/8711a72c-b077-487d-82f5-eb271a00e839","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"8711a72c-b077-487d-82f5-eb271a00e839","predictions":{"RoboJev-27B":0.10835135197083277,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.5725957321476373,"TypeSafe Jev 1.14":0.11,"Perplexity Decider":0.18706436508758423,"Liquid D1":0.09009300373428239,"Mercury Decide":0.9046505331728751,"Cloudflare Clef":0.0851,"cloudflare/clef-flash":0.1966,"cloudflare/clef-omni":0.093,"liquid/d1-ultra":0.09784416068877341,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.5341886165438249,"open/robojev-27b":null,"open/robojev-4b-v2":0.0023025598229782147,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.017755273617510888,"open/robojev-4b-v3@0.75":0.027346787282274982,"open/robojev-4b-v3":0.03693826366802302,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.06510708179002198,"respan/span-02":0.11868163,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.364119361614756,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0010986328125}},{"suite":"unseen","id":"rbm-ood/mit_franka/87c70b30-5a99-4411-9add-7790f2d5a297","task":"Pick up the spatula and stir the beans in the pot","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"87c70b30-5a99-4411-9add-7790f2d5a297","predictions":{"RoboJev-27B":0.07580996947450239,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.159236089034446,"TypeSafe Jev 1.14":0.24,"Perplexity Decider":0.15898825429842822,"Liquid D1":0.4378234991142019,"Mercury Decide":0.02595736016473944,"Cloudflare Clef":0.2621,"cloudflare/clef-flash":0.2726,"cloudflare/clef-omni":0.4766,"liquid/d1-ultra":0.1639626096311206,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.09763897119483515,"open/robojev-27b":null,"open/robojev-4b-v2":0.17328819801693726,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.09649050143553403,"open/robojev-4b-v3@0.75":0.13643297762397494,"open/robojev-4b-v3":0.19575444983810342,"openai/gpt-6-luna-decisions":0.24,"perplexity/pplx-decider-flash-v1.2":0.24051284371113987,"respan/span-02":0.118338525,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.13578076717485105,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0179443359375}},{"suite":"unseen","id":"rbm-ood/mit_franka/8965693b-a82e-44b7-be7b-084d5f46f8f4","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"8965693b-a82e-44b7-be7b-084d5f46f8f4","predictions":{"RoboJev-27B":0.6792328866067445,"GPT-6 Astra":0.05,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.6279698438585501,"TypeSafe Jev 1.14":0.57,"Perplexity Decider":0.6503002888038428,"Liquid D1":0.8354835371034369,"Mercury Decide":0.9579122684798184,"Cloudflare Clef":0.5406,"cloudflare/clef-flash":0.2287,"cloudflare/clef-omni":0.2907,"liquid/d1-ultra":0.7913111301945223,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.9235042517698707,"open/robojev-27b":null,"open/robojev-4b-v2":0.002106299096066607,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.02154587702420825,"open/robojev-4b-v3@0.75":0.027346787282274982,"open/robojev-4b-v3":0.03505281632584716,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1922711351944154,"respan/span-02":0.19689654,"typesafe/jev-1.13":0.5,"JEV-27B-VL (10 frames)":0.7206770880320276,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.5859375}},{"suite":"unseen","id":"rbm-ood/mit_franka/8beeb483-c9bd-4e6b-a2a7-fba7557db07e","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"8beeb483-c9bd-4e6b-a2a7-fba7557db07e","predictions":{"RoboJev-27B":0.29594581233721995,"GPT-6 Astra":0.16,"GPT-6.1 Sol":0.72,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.40483749663533986,"TypeSafe Jev 1.14":0.37,"Perplexity Decider":0.1916561994554071,"Liquid D1":0.867035763237924,"Mercury Decide":0.2942149597859341,"Cloudflare Clef":0.1581,"cloudflare/clef-flash":0.3142,"cloudflare/clef-omni":0.1098,"liquid/d1-ultra":0.46304398699442306,"open/intern-decision-4b":0.3201997500236374,"open/robojev-27b-v1@0.5":0.2847565598271211,"open/robojev-27b":null,"open/robojev-4b-v2":0.8267118019830628,"open/robojev-4b-v3@0.25":0.4687906503677368,"open/robojev-4b-v3@0.5":0.4345875784292984,"open/robojev-4b-v3@0.75":0.2666072781234324,"open/robojev-4b-v3":0.20445237038006636,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.5116403523809678,"respan/span-02":0.78412414,"typesafe/jev-1.13":0.39,"JEV-27B-VL (10 frames)":0.27361594361963215,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.037353515625}},{"suite":"unseen","id":"rbm-ood/mit_franka/8c333dd9-3d99-448e-ae58-b681b36d502b","task":"Fold the towel in half","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"8c333dd9-3d99-448e-ae58-b681b36d502b","predictions":{"RoboJev-27B":0.08199942020236345,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.3114030278774693,"TypeSafe Jev 1.14":0.58,"Perplexity Decider":0.17433867711051176,"Liquid D1":0.32082130082460697,"Mercury Decide":0.13296423676207594,"Cloudflare Clef":0.2826,"cloudflare/clef-flash":0.2937,"cloudflare/clef-omni":0.151,"liquid/d1-ultra":0.10691174864063513,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.19222964047575963,"open/robojev-27b":null,"open/robojev-4b-v2":0.7448684972957533,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.07585817666120565,"open/robojev-4b-v3@0.75":0.019292242704938834,"open/robojev-4b-v3":0.008764341864947102,"openai/gpt-6-luna-decisions":0.12,"perplexity/pplx-decider-flash-v1.2":0.277903756842483,"respan/span-02":0.6572207,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.18928996341398543,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.048828125}},{"suite":"unseen","id":"rbm-ood/mit_franka/8c794ff2-6cfe-405e-97d2-a4d57b8be79b","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"8c794ff2-6cfe-405e-97d2-a4d57b8be79b","predictions":{"RoboJev-27B":0.009426931802292359,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.012242536433032367,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.0317334781202501,"Liquid D1":0.05340332829327471,"Mercury Decide":0.0023231619894602865,"Cloudflare Clef":0.1797,"cloudflare/clef-flash":0.1927,"cloudflare/clef-omni":0.1074,"liquid/d1-ultra":0.16396261447115354,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.0009421727438161061,"open/robojev-27b":null,"open/robojev-4b-v2":0.004293165515526464,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.012842048097105568,"open/robojev-4b-v3@0.75":0.010731211960485985,"open/robojev-4b-v3":0.008764341864947102,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.09151716345631182,"respan/span-02":0.5605075,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.012476509041938146,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000732421875}},{"suite":"unseen","id":"rbm-ood/mit_franka/8cb48ffc-25d4-4337-a07d-963b24e888bc","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"8cb48ffc-25d4-4337-a07d-963b24e888bc","predictions":{"RoboJev-27B":0.45175782781874924,"GPT-6 Astra":0.38,"GPT-6.1 Sol":0.86,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.5191871981766353,"TypeSafe Jev 1.14":0.57,"Perplexity Decider":0.530917725424724,"Liquid D1":0.8354835411997897,"Mercury Decide":0.22270013882530884,"Cloudflare Clef":0.4584,"cloudflare/clef-flash":0.39,"cloudflare/clef-omni":0.2708,"liquid/d1-ultra":0.5855387423586069,"open/intern-decision-4b":0.36247442200877295,"open/robojev-27b-v1@0.5":0.3799604886771262,"open/robojev-27b":null,"open/robojev-4b-v2":0.007644678711335276,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.0909052424413583,"open/robojev-4b-v3@0.75":0.07585818674635426,"open/robojev-4b-v3":0.06195489972932116,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.5833644604039013,"respan/span-02":0.64546627,"typesafe/jev-1.13":0.35,"JEV-27B-VL (10 frames)":0.5947006637657125,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.3984375}},{"suite":"unseen","id":"rbm-ood/mit_franka/8d12f346-fc65-40a8-8ffe-131ef8a43d2c","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"8d12f346-fc65-40a8-8ffe-131ef8a43d2c","predictions":{"RoboJev-27B":0.6005235142959267,"GPT-6 Astra":0.82,"GPT-6.1 Sol":0.72,"Claude Opus 5.5":0.45,"Claude Sonnet 5.5":0.35,"JEV-27B-VL":0.5268729585790383,"TypeSafe Jev 1.14":0.46,"Perplexity Decider":0.5091361366429218,"Liquid D1":0.7549149813536518,"Mercury Decide":0.6224593312018546,"Cloudflare Clef":0.5066,"cloudflare/clef-flash":0.481,"cloudflare/clef-omni":0.2897,"liquid/d1-ultra":0.3907210731786067,"open/intern-decision-4b":0.34810523633137336,"open/robojev-27b-v1@0.5":0.699618541680638,"open/robojev-27b":null,"open/robojev-4b-v2":0.42250462885325446,"open/robojev-4b-v3@0.25":0.7772998809814453,"open/robojev-4b-v3@0.5":0.7016700331917485,"open/robojev-4b-v3@0.75":0.36918510345682914,"open/robojev-4b-v3":0.1125237519028778,"openai/gpt-6-luna-decisions":0.1,"perplexity/pplx-decider-flash-v1.2":0.5164116057906928,"respan/span-02":0.22316694,"typesafe/jev-1.13":0.5,"JEV-27B-VL (10 frames)":0.4929385617924629,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01031494140625}},{"suite":"unseen","id":"rbm-ood/mit_franka/8d1c9687-085e-40e3-b7ab-e693d917f020","task":"Pick up the spatula and stir the beans in the pot","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"8d1c9687-085e-40e3-b7ab-e693d917f020","predictions":{"RoboJev-27B":0.41674053177222403,"GPT-6 Astra":0.8,"GPT-6.1 Sol":0.83,"Claude Opus 5.5":0.62,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.07724640879930741,"TypeSafe Jev 1.14":0.24,"Perplexity Decider":0.1767315361604554,"Liquid D1":0.0803574622150194,"Mercury Decide":0.02931222757148327,"Cloudflare Clef":0.2539,"cloudflare/clef-flash":0.1579,"cloudflare/clef-omni":0.0615,"liquid/d1-ultra":0.4876613324012321,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.16321939363125548,"open/robojev-27b":null,"open/robojev-4b-v2":0.042087729958985645,"open/robojev-4b-v3@0.25":0.13296423852443695,"open/robojev-4b-v3@0.5":0.1447586588133107,"open/robojev-4b-v3@0.75":0.13643297762397494,"open/robojev-4b-v3":0.11806640532074496,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.23194110638669055,"respan/span-02":0.10792093,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.17087233514481392,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.054931640625}},{"suite":"unseen","id":"rbm-ood/mit_franka/8d857e6b-d6a6-4799-ac84-57d854b1c353","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"8d857e6b-d6a6-4799-ac84-57d854b1c353","predictions":{"RoboJev-27B":0.9848881375514386,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":0.9968620731384822,"TypeSafe Jev 1.14":0.9,"Perplexity Decider":0.995056909034457,"Liquid D1":0.9984988180001244,"Mercury Decide":0.9964063980388481,"Cloudflare Clef":0.971,"cloudflare/clef-flash":0.8833,"cloudflare/clef-omni":0.1355,"liquid/d1-ultra":0.9434163438471367,"open/intern-decision-4b":0.844739173437523,"open/robojev-27b-v1@0.5":0.9984700422889515,"open/robojev-27b":null,"open/robojev-4b-v2":0.3385768147857754,"open/robojev-4b-v3@0.25":0.9890130758285522,"open/robojev-4b-v3@0.5":0.9900999205272626,"open/robojev-4b-v3@0.75":0.9818023083761724,"open/robojev-4b-v3":0.9684435763811455,"openai/gpt-6-luna-decisions":0.99,"perplexity/pplx-decider-flash-v1.2":0.987272846842837,"respan/span-02":0.9245087,"typesafe/jev-1.13":0.82,"JEV-27B-VL (10 frames)":0.971673102735902,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.083984375}},{"suite":"unseen","id":"rbm-ood/mit_franka/9004622a-b59a-4aab-b02c-6d0ac4c4bf79","task":"Fold the towel in half","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"9004622a-b59a-4aab-b02c-6d0ac4c4bf79","predictions":{"RoboJev-27B":0.023090620501708053,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.07141946421431616,"TypeSafe Jev 1.14":0.18,"Perplexity Decider":0.07941910774611667,"Liquid D1":0.46879062662624377,"Mercury Decide":0.0159063885045792,"Cloudflare Clef":0.21,"cloudflare/clef-flash":0.2802,"cloudflare/clef-omni":0.1186,"liquid/d1-ultra":0.06209063817006961,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.009478248788910962,"open/robojev-27b":null,"open/robojev-4b-v2":0.13296424849235422,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.02612421708095358,"open/robojev-4b-v3@0.75":0.013576917981093352,"open/robojev-4b-v3":0.010300413398065098,"openai/gpt-6-luna-decisions":0.11,"perplexity/pplx-decider-flash-v1.2":0.1608304029382304,"respan/span-02":0.54039943,"typesafe/jev-1.13":0.18,"JEV-27B-VL (10 frames)":0.11765496796381081,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0029754638671875}},{"suite":"unseen","id":"rbm-ood/mit_franka/914335e2-47c0-4c8c-9a27-59cff97f9807","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"914335e2-47c0-4c8c-9a27-59cff97f9807","predictions":{"RoboJev-27B":0.2750793145873082,"GPT-6 Astra":0.27,"GPT-6.1 Sol":0.62,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.19994442484436153,"TypeSafe Jev 1.14":0.2,"Perplexity Decider":0.2634251420039884,"Liquid D1":0.5,"Mercury Decide":0.10669060175672705,"Cloudflare Clef":0.2933,"cloudflare/clef-flash":0.3934,"cloudflare/clef-omni":0.1857,"liquid/d1-ultra":0.3017033426880089,"open/intern-decision-4b":0.3201997500236374,"open/robojev-27b-v1@0.5":0.17360294153677477,"open/robojev-27b":null,"open/robojev-4b-v2":0.22270012827216223,"open/robojev-4b-v3@0.25":0.7057850360870361,"open/robojev-4b-v3@0.5":0.7536956923154546,"open/robojev-4b-v3@0.75":0.38315208923909133,"open/robojev-4b-v3":0.2227001494864363,"openai/gpt-6-luna-decisions":0.09,"perplexity/pplx-decider-flash-v1.2":0.4190766969537818,"respan/span-02":0.4693217,"typesafe/jev-1.13":0.45,"JEV-27B-VL (10 frames)":0.25177449346084546,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0145263671875}},{"suite":"unseen","id":"rbm-ood/mit_franka/915d82b0-fb49-4257-8c60-668ead0af980","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"915d82b0-fb49-4257-8c60-668ead0af980","predictions":{"RoboJev-27B":0.9105146688172823,"GPT-6 Astra":0.93,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8666215492936009,"TypeSafe Jev 1.14":0.72,"Perplexity Decider":0.9342735173105992,"Liquid D1":0.8175744850834649,"Mercury Decide":0.9770226285428089,"Cloudflare Clef":0.4771,"cloudflare/clef-flash":0.4274,"cloudflare/clef-omni":0.4295,"liquid/d1-ultra":0.8071467729059975,"open/intern-decision-4b":0.5313278281391198,"open/robojev-27b-v1@0.5":0.9766288595915257,"open/robojev-27b":null,"open/robojev-4b-v2":0.002631674205642126,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.10858632498619036,"open/robojev-4b-v3@0.75":0.1050005837572588,"open/robojev-4b-v3":0.1637708093883215,"openai/gpt-6-luna-decisions":0.37,"perplexity/pplx-decider-flash-v1.2":0.7192773430518613,"respan/span-02":0.27702376,"typesafe/jev-1.13":0.65,"JEV-27B-VL (10 frames)":0.8937753299087831,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.4375}},{"suite":"unseen","id":"rbm-ood/mit_franka/91dcc5c5-1b64-4222-ae15-45ddbff63d64","task":"Pull a tissue from the tissue box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"91dcc5c5-1b64-4222-ae15-45ddbff63d64","predictions":{"RoboJev-27B":0.45836871999195455,"GPT-6 Astra":0.22,"GPT-6.1 Sol":0.12,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.3384224804076599,"TypeSafe Jev 1.14":0.36,"Perplexity Decider":0.3998920827658821,"Liquid D1":0.5,"Mercury Decide":0.10669059323555342,"Cloudflare Clef":0.4118,"cloudflare/clef-flash":0.3275,"cloudflare/clef-omni":0.4113,"liquid/d1-ultra":0.35608979338774427,"open/intern-decision-4b":0.5313278281391198,"open/robojev-27b-v1@0.5":0.39539093652993057,"open/robojev-27b":null,"open/robojev-4b-v2":0.2905205683918636,"open/robojev-4b-v3@0.25":0.8175744414329529,"open/robojev-4b-v3@0.5":0.8848796562508825,"open/robojev-4b-v3@0.75":0.8411309059812064,"open/robojev-4b-v3":0.6070151330675095,"openai/gpt-6-luna-decisions":0.06,"perplexity/pplx-decider-flash-v1.2":0.5736613807319787,"respan/span-02":0.75959873,"typesafe/jev-1.13":0.47,"JEV-27B-VL (10 frames)":0.37803896905916845,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.021240234375}},{"suite":"unseen","id":"rbm-ood/mit_franka/92704c22-37e3-47d7-8d98-f9a2660e59e1","task":"Pull a tissue from the tissue box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"92704c22-37e3-47d7-8d98-f9a2660e59e1","predictions":{"RoboJev-27B":0.19083056221029754,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.06,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":0.13692423957654168,"TypeSafe Jev 1.14":0.14,"Perplexity Decider":0.20922350999941314,"Liquid D1":0.19193278182505782,"Mercury Decide":0.05340332697504391,"Cloudflare Clef":0.287,"cloudflare/clef-flash":0.3306,"cloudflare/clef-omni":0.1948,"liquid/d1-ultra":0.200654060198294,"open/intern-decision-4b":0.36247442200877295,"open/robojev-27b-v1@0.5":0.00616938539948894,"open/robojev-27b":null,"open/robojev-4b-v2":0.2385375068070853,"open/robojev-4b-v3@0.25":0.3208213150501251,"open/robojev-4b-v3@0.5":0.153095448827493,"open/robojev-4b-v3@0.75":0.06076252040232631,"open/robojev-4b-v3":0.025548296110078653,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.29883555507525494,"respan/span-02":0.17456709,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.33921204714019326,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00170135498046875}},{"suite":"unseen","id":"rbm-ood/mit_franka/94a8857c-bbaf-4d02-9582-368991ecc094","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"94a8857c-bbaf-4d02-9582-368991ecc094","predictions":{"RoboJev-27B":0.811471386621151,"GPT-6 Astra":0.9,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.7461303832340316,"TypeSafe Jev 1.14":0.67,"Perplexity Decider":0.8351341648115164,"Liquid D1":0.9669140213729421,"Mercury Decide":0.9149009584734678,"Cloudflare Clef":0.5531,"cloudflare/clef-flash":0.6074,"cloudflare/clef-omni":0.652,"liquid/d1-ultra":0.8291578031974798,"open/intern-decision-4b":0.36247442200877295,"open/robojev-27b-v1@0.5":0.9052269197953929,"open/robojev-27b":null,"open/robojev-4b-v2":0.003757049695787553,"open/robojev-4b-v3@0.25":0.3775406777858734,"open/robojev-4b-v3@0.5":0.2847434534005251,"open/robojev-4b-v3@0.75":0.1050005837572588,"open/robojev-4b-v3":0.047919347698515906,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.42006491777781846,"respan/span-02":0.25102895,"typesafe/jev-1.13":0.62,"JEV-27B-VL (10 frames)":0.874088658539228,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0247802734375}},{"suite":"unseen","id":"rbm-ood/mit_franka/95359920-4e27-4363-a133-2ef7e90de9ff","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"95359920-4e27-4363-a133-2ef7e90de9ff","predictions":{"RoboJev-27B":0.0551180459500782,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.3197204272346444,"TypeSafe Jev 1.14":0.24,"Perplexity Decider":0.19151063684721154,"Liquid D1":0.7057850278370112,"Mercury Decide":0.09534945847239201,"Cloudflare Clef":0.5709,"cloudflare/clef-flash":0.5715,"cloudflare/clef-omni":0.2832,"liquid/d1-ultra":0.19285322342991418,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.027753033230411252,"open/robojev-27b":null,"open/robojev-4b-v2":0.002631674205642126,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.01664357488299338,"open/robojev-4b-v3@0.75":0.005282311488788821,"open/robojev-4b-v3":0.0019267345803236512,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.47142760860535343,"respan/span-02":0.14794618,"typesafe/jev-1.13":0.38,"JEV-27B-VL (10 frames)":0.1830542465712092,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.314453125}},{"suite":"unseen","id":"rbm-ood/mit_franka/95bef17e-ae03-4040-ac10-c15c01e2cce3","task":"Pick up the spoon and place it inside the cup","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"95bef17e-ae03-4040-ac10-c15c01e2cce3","predictions":{"RoboJev-27B":0.00879869101489035,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.025022043124074717,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.03195208584502757,"Liquid D1":0.05665242052980391,"Mercury Decide":0.007577242612510723,"Cloudflare Clef":0.0946,"cloudflare/clef-flash":0.2162,"cloudflare/clef-omni":0.1087,"liquid/d1-ultra":0.10691173515542983,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.001032759420683784,"open/robojev-27b":null,"open/robojev-4b-v2":0.002751490629587489,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.010566189227213266,"open/robojev-4b-v3@0.75":0.007532610956861541,"open/robojev-4b-v3":0.008304581719395627,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.05642911977604097,"respan/span-02":0.16678405,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.012507230868064666,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01361083984375}},{"suite":"unseen","id":"rbm-ood/mit_franka/95d0a35e-ae23-4a48-bdff-00abf0713b26","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"95d0a35e-ae23-4a48-bdff-00abf0713b26","predictions":{"RoboJev-27B":0.9244814686049099,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.9334936732795418,"TypeSafe Jev 1.14":0.88,"Perplexity Decider":0.9682593858135574,"Liquid D1":0.9896718458433413,"Mercury Decide":0.997199073563536,"Cloudflare Clef":0.8585,"cloudflare/clef-flash":0.8739,"cloudflare/clef-omni":0.6543,"liquid/d1-ultra":0.9629620116846854,"open/intern-decision-4b":0.8940776460411956,"open/robojev-27b-v1@0.5":0.9856582378077987,"open/robojev-27b":null,"open/robojev-4b-v2":0.9886181217784766,"open/robojev-4b-v3@0.25":0.9902915358543396,"open/robojev-4b-v3@0.5":0.9900999205272626,"open/robojev-4b-v3@0.75":0.9838116535048939,"open/robojev-4b-v3":0.9700628546674281,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9760249467441207,"respan/span-02":0.40382007,"typesafe/jev-1.13":0.89,"JEV-27B-VL (10 frames)":0.8737616932160772,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.494140625}},{"suite":"unseen","id":"rbm-ood/mit_franka/9961c289-ba40-429b-8d89-1147d31dc746","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"9961c289-ba40-429b-8d89-1147d31dc746","predictions":{"RoboJev-27B":0.8276129362190296,"GPT-6 Astra":0.8,"GPT-6.1 Sol":0.62,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.68,"JEV-27B-VL":0.8212457286007666,"TypeSafe Jev 1.14":0.66,"Perplexity Decider":0.8590495107775669,"Liquid D1":0.8519528019683106,"Mercury Decide":0.9324533055754921,"Cloudflare Clef":0.4961,"cloudflare/clef-flash":0.5911,"cloudflare/clef-omni":0.7588,"liquid/d1-ultra":0.620965177756194,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.9355567260540476,"open/robojev-27b":null,"open/robojev-4b-v2":0.003593602817215226,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.0909052424413583,"open/robojev-4b-v3@0.75":0.13643297762397494,"open/robojev-4b-v3":0.10720967645457925,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.7767547687082604,"respan/span-02":0.7020196,"typesafe/jev-1.13":0.75,"JEV-27B-VL (10 frames)":0.7730579580426311,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1240234375}},{"suite":"unseen","id":"rbm-ood/mit_franka/9aa6ff0d-a0c0-4952-9faf-14df41ef387a","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"9aa6ff0d-a0c0-4952-9faf-14df41ef387a","predictions":{"RoboJev-27B":0.003280756386412707,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.006547481618477301,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.033875498337586574,"Liquid D1":0.03308597981882656,"Mercury Decide":0.0029810323478672196,"Cloudflare Clef":0.1912,"cloudflare/clef-flash":0.4707,"cloudflare/clef-omni":0.1321,"liquid/d1-ultra":0.05927724969247303,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.00020196414806087682,"open/robojev-27b":null,"open/robojev-4b-v2":0.004293165515526464,"open/robojev-4b-v3@0.25":0.022977370768785477,"open/robojev-4b-v3@0.5":0.010566189227213266,"open/robojev-4b-v3@0.75":0.008992055872561407,"open/robojev-4b-v3":0.010300413398065098,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.07270933110123498,"respan/span-02":0.03762569,"typesafe/jev-1.13":0.03,"JEV-27B-VL (10 frames)":0.003317112687126557,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.001983642578125}},{"suite":"unseen","id":"rbm-ood/mit_franka/9c76fad2-fd74-4fda-9625-6694564dd16e","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"9c76fad2-fd74-4fda-9625-6694564dd16e","predictions":{"RoboJev-27B":0.7617176631713217,"GPT-6 Astra":0.9,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.45,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.691789911339813,"TypeSafe Jev 1.14":0.77,"Perplexity Decider":0.7226711557810231,"Liquid D1":0.7772998508568416,"Mercury Decide":0.8354835371034369,"Cloudflare Clef":0.6182,"cloudflare/clef-flash":0.4005,"cloudflare/clef-omni":0.1034,"liquid/d1-ultra":0.5974659344706373,"open/intern-decision-4b":0.37709365395745764,"open/robojev-27b-v1@0.5":0.7315853309352855,"open/robojev-27b":null,"open/robojev-4b-v2":0.0034372413231743533,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.09649050143553403,"open/robojev-4b-v3@0.75":0.08463674788192488,"open/robojev-4b-v3":0.045499872888298876,"openai/gpt-6-luna-decisions":0.11,"perplexity/pplx-decider-flash-v1.2":0.678197713470753,"respan/span-02":0.7015326,"typesafe/jev-1.13":0.44,"JEV-27B-VL (10 frames)":0.8481492962363767,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00628662109375}},{"suite":"unseen","id":"rbm-ood/mit_franka/9d084f85-1caf-47eb-86e1-6e04360bbcf5","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"9d084f85-1caf-47eb-86e1-6e04360bbcf5","predictions":{"RoboJev-27B":0.004086376116329098,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.006277612264060087,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.03073113255427813,"Liquid D1":0.07585818419975078,"Mercury Decide":0.005220125572652333,"Cloudflare Clef":0.1973,"cloudflare/clef-flash":0.1242,"cloudflare/clef-omni":0.1754,"liquid/d1-ultra":0.11671092643799169,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.00017134838059012998,"open/robojev-27b":null,"open/robojev-4b-v2":0.003593602817215226,"open/robojev-4b-v3@0.25":0.02595735713839531,"open/robojev-4b-v3@0.5":0.011276606158891207,"open/robojev-4b-v3@0.75":0.008992055872561407,"open/robojev-4b-v3":0.009249319533522623,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.15582945608105275,"respan/span-02":0.034641348,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.006164059066189492,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0057373046875}},{"suite":"unseen","id":"rbm-ood/mit_franka/9f5b84f6-26f9-40b1-8bb4-a133beb51837","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"9f5b84f6-26f9-40b1-8bb4-a133beb51837","predictions":{"RoboJev-27B":0.5525637843311685,"GPT-6 Astra":0.25,"GPT-6.1 Sol":0.25,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.35,"JEV-27B-VL":0.5631456222291983,"TypeSafe Jev 1.14":0.53,"Perplexity Decider":0.4729865630171605,"Liquid D1":0.8175744806385543,"Mercury Decide":0.46879062662624377,"Cloudflare Clef":0.2582,"cloudflare/clef-flash":0.4419,"cloudflare/clef-omni":0.3633,"liquid/d1-ultra":0.5123386675987679,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.7094525940580091,"open/robojev-27b":null,"open/robojev-4b-v2":0.7094794316081363,"open/robojev-4b-v3@0.25":0.851952850818634,"open/robojev-4b-v3@0.5":0.2847434534005251,"open/robojev-4b-v3@0.75":0.13643297762397494,"open/robojev-4b-v3":0.047919347698515906,"openai/gpt-6-luna-decisions":0.16,"perplexity/pplx-decider-flash-v1.2":0.7069261846358056,"respan/span-02":0.72955257,"typesafe/jev-1.13":0.65,"JEV-27B-VL (10 frames)":0.39459295885798,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00360107421875}},{"suite":"unseen","id":"rbm-ood/mit_franka/a75c2cac-349d-4d15-93ce-ad2f1f7877bc","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"a75c2cac-349d-4d15-93ce-ad2f1f7877bc","predictions":{"RoboJev-27B":0.027968607893798816,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.012477588039455843,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.0530456412419217,"Liquid D1":0.056652426900697224,"Mercury Decide":0.010986940039882433,"Cloudflare Clef":0.2694,"cloudflare/clef-flash":0.2576,"cloudflare/clef-omni":0.1899,"liquid/d1-ultra":0.18528537315384558,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.0056750499193615744,"open/robojev-27b":null,"open/robojev-4b-v2":0.005361080321059209,"open/robojev-4b-v3@0.25":0.622459352016449,"open/robojev-4b-v3@0.5":0.19040689770918212,"open/robojev-4b-v3@0.75":0.07585818674635426,"open/robojev-4b-v3":0.053129261209546814,"openai/gpt-6-luna-decisions":0.06,"perplexity/pplx-decider-flash-v1.2":0.21611265413533973,"respan/span-02":0.13707338,"typesafe/jev-1.13":0.12,"JEV-27B-VL (10 frames)":0.016653582033869012,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.007354736328125}},{"suite":"unseen","id":"rbm-ood/mit_franka/ab343a28-eb35-4e31-99b9-ba5fa8225d79","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"ab343a28-eb35-4e31-99b9-ba5fa8225d79","predictions":{"RoboJev-27B":0.10563706229369425,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.62,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.40855449727520377,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.3771454079233868,"Liquid D1":0.18242552825126704,"Mercury Decide":0.5312093733737563,"Cloudflare Clef":0.1903,"cloudflare/clef-flash":0.1859,"cloudflare/clef-omni":0.1137,"liquid/d1-ultra":0.5246623165651004,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.27799120662089366,"open/robojev-27b":null,"open/robojev-4b-v2":0.002751490629587489,"open/robojev-4b-v3@0.25":0.10669060051441193,"open/robojev-4b-v3@0.5":0.020201721614979237,"open/robojev-4b-v3@0.75":0.01011736424150334,"open/robojev-4b-v3":0.005691671058411752,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.3110611165716977,"respan/span-02":0.17626889,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.24760450094674574,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00262451171875}},{"suite":"unseen","id":"rbm-ood/mit_franka/aced9fe0-caee-4790-b4b7-e4ef20febf1b","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"aced9fe0-caee-4790-b4b7-e4ef20febf1b","predictions":{"RoboJev-27B":0.09261260430080476,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.03621495088184048,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.05633246509001532,"Liquid D1":0.32082130082460697,"Mercury Decide":0.008577486752172713,"Cloudflare Clef":0.1957,"cloudflare/clef-flash":0.3207,"cloudflare/clef-omni":0.4473,"liquid/d1-ultra":0.2006540753001129,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.011176796751655135,"open/robojev-27b":null,"open/robojev-4b-v2":0.0025170615300917137,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.03164395527984847,"open/robojev-4b-v3@0.75":0.027346787282274982,"open/robojev-4b-v3":0.020659669708358676,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.08123864606043567,"respan/span-02":0.18012835,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.05460126393411666,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.640625}},{"suite":"unseen","id":"rbm-ood/mit_franka/aeeb8a39-2eff-4ce2-95da-b3dcf51a7346","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"aeeb8a39-2eff-4ce2-95da-b3dcf51a7346","predictions":{"RoboJev-27B":0.18077996931838666,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.07,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.062077686422816504,"TypeSafe Jev 1.14":0.16,"Perplexity Decider":0.14291828356504127,"Liquid D1":0.7057850216484838,"Mercury Decide":0.06754669067036073,"Cloudflare Clef":0.3892,"cloudflare/clef-flash":0.3291,"cloudflare/clef-omni":0.277,"liquid/d1-ultra":0.18528537315384558,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.016776262332611314,"open/robojev-27b":null,"open/robojev-4b-v2":0.014826107129937436,"open/robojev-4b-v3@0.25":0.07585817575454712,"open/robojev-4b-v3@0.5":0.04343408155889982,"open/robojev-4b-v3@0.75":0.032519444419615386,"open/robojev-4b-v3":0.021788411170123766,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3268809263437305,"respan/span-02":0.061856944,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.04832073029676459,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0028076171875}},{"suite":"unseen","id":"rbm-ood/mit_franka/b00d51d5-9ad6-45cf-aca8-03df33c632e7","task":"Pour the pebbles from the cup onto the plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"b00d51d5-9ad6-45cf-aca8-03df33c632e7","predictions":{"RoboJev-27B":0.8117948854005039,"GPT-6 Astra":0.85,"GPT-6.1 Sol":0.87,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.46917113044965597,"TypeSafe Jev 1.14":0.17,"Perplexity Decider":0.5533770702512331,"Liquid D1":0.34864513533394575,"Mercury Decide":0.8807970795424088,"Cloudflare Clef":0.2988,"cloudflare/clef-flash":0.217,"cloudflare/clef-omni":0.1685,"liquid/d1-ultra":0.2617952399152932,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.8868750939118623,"open/robojev-27b":null,"open/robojev-4b-v2":0.0046922355486094065,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.1447586588133107,"open/robojev-4b-v3@0.75":0.09432751595727837,"open/robojev-4b-v3":0.06195489972932116,"openai/gpt-6-luna-decisions":0.09,"perplexity/pplx-decider-flash-v1.2":0.2806720155375502,"respan/span-02":0.19574718,"typesafe/jev-1.13":0.49,"JEV-27B-VL (10 frames)":0.6125088583086459,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0791015625}},{"suite":"unseen","id":"rbm-ood/mit_franka/b013712a-8ae8-4db6-a783-2208a5495aec","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"b013712a-8ae8-4db6-a783-2208a5495aec","predictions":{"RoboJev-27B":0.01663868614821591,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.04741394621072644,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.07693865148884187,"Liquid D1":0.11920292202211755,"Mercury Decide":0.022977367610185033,"Cloudflare Clef":0.3052,"cloudflare/clef-flash":0.2794,"cloudflare/clef-omni":0.1644,"liquid/d1-ultra":0.13286531769027898,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.0027561214060864386,"open/robojev-27b":null,"open/robojev-4b-v2":0.0031445701339940513,"open/robojev-4b-v3@0.25":0.03308597952127457,"open/robojev-4b-v3@0.5":0.01560037702180545,"open/robojev-4b-v3@0.75":0.013576917981093352,"open/robojev-4b-v3":0.009760866998496955,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.3071085532400043,"respan/span-02":0.15295589,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.048169125638487346,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00628662109375}},{"suite":"unseen","id":"rbm-ood/mit_franka/b0a316a8-9cad-428f-a3e6-0662ff0412dd","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"b0a316a8-9cad-428f-a3e6-0662ff0412dd","predictions":{"RoboJev-27B":0.002253660219626458,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.00041603437975631843,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.008551354104829606,"Liquid D1":0.05340333130637379,"Mercury Decide":0.0005193047446144226,"Cloudflare Clef":0.0734,"cloudflare/clef-flash":0.2429,"cloudflare/clef-omni":0.1614,"liquid/d1-ultra":0.04072481108803403,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":4.682317702927285e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.0025170615300917137,"open/robojev-4b-v3@0.25":0.01243165135383606,"open/robojev-4b-v3@0.5":0.0037133326112963453,"open/robojev-4b-v3@0.75":0.0037017607703716303,"open/robojev-4b-v3":0.003138491707937668,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.022653638062154677,"respan/span-02":0.15432745,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.0024594248293690574,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000667572021484375}},{"suite":"unseen","id":"rbm-ood/mit_franka/b2b95e51-512a-4a64-8087-c146de3145f8","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"b2b95e51-512a-4a64-8087-c146de3145f8","predictions":{"RoboJev-27B":0.5533615793760408,"GPT-6 Astra":0.07,"GPT-6.1 Sol":0.12,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.647539666327988,"TypeSafe Jev 1.14":0.47,"Perplexity Decider":0.6490633112870806,"Liquid D1":0.5312093733737563,"Mercury Decide":0.8670357494949105,"Cloudflare Clef":0.4484,"cloudflare/clef-flash":0.5545,"cloudflare/clef-omni":0.5976,"liquid/d1-ultra":0.4264895721219793,"open/intern-decision-4b":0.5,"open/robojev-27b-v1@0.5":0.42364472357568234,"open/robojev-27b":null,"open/robojev-4b-v2":0.004293165515526464,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.06312881727672377,"open/robojev-4b-v3@0.75":0.032519444419615386,"open/robojev-4b-v3":0.024229601278625137,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.8180744753367031,"respan/span-02":0.63311374,"typesafe/jev-1.13":0.61,"JEV-27B-VL (10 frames)":0.6204706540497474,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.67578125}},{"suite":"unseen","id":"rbm-ood/mit_franka/b428c0c7-80ed-4dd8-8c42-8000bea2fd78","task":"Pull a tissue from the tissue box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"b428c0c7-80ed-4dd8-8c42-8000bea2fd78","predictions":{"RoboJev-27B":0.14065065165088167,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.3384224804076599,"TypeSafe Jev 1.14":0.37,"Perplexity Decider":0.26722642393330603,"Liquid D1":0.7057850340255386,"Mercury Decide":0.06008664344151498,"Cloudflare Clef":0.6453,"cloudflare/clef-flash":0.3395,"cloudflare/clef-omni":0.2497,"liquid/d1-ultra":0.3122040817744257,"open/intern-decision-4b":0.37709365395745764,"open/robojev-27b-v1@0.5":0.12919313908895688,"open/robojev-27b":null,"open/robojev-4b-v2":0.87699602202752,"open/robojev-4b-v3@0.25":0.8807970285415649,"open/robojev-4b-v3@0.5":0.9193991005705059,"open/robojev-4b-v3@0.75":0.915363252118075,"open/robojev-4b-v3":0.9202429190773747,"openai/gpt-6-luna-decisions":0.13,"perplexity/pplx-decider-flash-v1.2":0.436046681150594,"respan/span-02":0.66851866,"typesafe/jev-1.13":0.63,"JEV-27B-VL (10 frames)":0.388554803065951,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.004058837890625}},{"suite":"unseen","id":"rbm-ood/mit_franka/b5dd5264-67f9-41c0-8aa6-07a103b19e23","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"b5dd5264-67f9-41c0-8aa6-07a103b19e23","predictions":{"RoboJev-27B":0.012253730856961863,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.00512453541946855,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.024993580697118815,"Liquid D1":0.07585817688736327,"Mercury Decide":0.0015011823572479975,"Cloudflare Clef":0.2291,"cloudflare/clef-flash":0.1971,"cloudflare/clef-omni":0.2214,"liquid/d1-ultra":0.05400543049217903,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.003949277936745374,"open/robojev-27b":null,"open/robojev-4b-v2":0.006692850868879798,"open/robojev-4b-v3@0.25":0.07585817575454712,"open/robojev-4b-v3@0.5":0.02612421708095358,"open/robojev-4b-v3@0.75":0.0171641516746209,"open/robojev-4b-v3":0.01582154176925847,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.13854759087156823,"respan/span-02":0.15786526,"typesafe/jev-1.13":0.33,"JEV-27B-VL (10 frames)":0.015993690682145602,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0005035400390625}},{"suite":"unseen","id":"rbm-ood/mit_franka/b8821982-69c0-4dcd-bdeb-ddce09d47295","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"b8821982-69c0-4dcd-bdeb-ddce09d47295","predictions":{"RoboJev-27B":0.5587227356883405,"GPT-6 Astra":0.22,"GPT-6.1 Sol":0.84,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.5422027347558217,"TypeSafe Jev 1.14":0.33,"Perplexity Decider":0.4855046370957887,"Liquid D1":0.679178699175393,"Mercury Decide":0.8175744828610095,"Cloudflare Clef":0.4647,"cloudflare/clef-flash":0.2718,"cloudflare/clef-omni":0.1255,"liquid/d1-ultra":0.6325127074476207,"open/intern-decision-4b":0.3201997500236374,"open/robojev-27b-v1@0.5":0.5723303324181218,"open/robojev-27b":null,"open/robojev-4b-v2":0.943347575104978,"open/robojev-4b-v3@0.25":0.9046505093574524,"open/robojev-4b-v3@0.5":0.8381784546520696,"open/robojev-4b-v3@0.75":0.6713474489845783,"open/robojev-4b-v3":0.44586519550865067,"openai/gpt-6-luna-decisions":0.64,"perplexity/pplx-decider-flash-v1.2":0.7033391787861817,"respan/span-02":0.8281096,"typesafe/jev-1.13":0.5,"JEV-27B-VL (10 frames)":0.43932590458148113,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.177734375}},{"suite":"unseen","id":"rbm-ood/mit_franka/b9a63762-7e22-4194-85a2-93d5666d876c","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"b9a63762-7e22-4194-85a2-93d5666d876c","predictions":{"RoboJev-27B":0.007490089721252099,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.0014571395406965922,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.014406547739749713,"Liquid D1":0.02297736857193652,"Mercury Decide":0.0011695102781105248,"Cloudflare Clef":0.1237,"cloudflare/clef-flash":0.1521,"cloudflare/clef-omni":0.0893,"liquid/d1-ultra":0.09784416692216301,"open/intern-decision-4b":0.12511350509772579,"open/robojev-27b-v1@0.5":0.00013714940961484447,"open/robojev-27b":null,"open/robojev-4b-v2":0.0017624512139676404,"open/robojev-4b-v3@0.25":0.020332353189587593,"open/robojev-4b-v3@0.5":0.007144725422878838,"open/robojev-4b-v3@0.75":0.005282311488788821,"open/robojev-4b-v3":0.004584702275672031,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.13406460085866131,"respan/span-02":0.05027268,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.0027129629008878606,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0244140625}},{"suite":"unseen","id":"rbm-ood/mit_franka/b9d0e32f-df63-49b7-80cf-96feb65677ce","task":"Pull a tissue from the tissue box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"b9d0e32f-df63-49b7-80cf-96feb65677ce","predictions":{"RoboJev-27B":0.098526539699927,"GPT-6 Astra":0.06,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.07947125509083774,"TypeSafe Jev 1.14":0.25,"Perplexity Decider":0.13347267299283389,"Liquid D1":0.07585818211049715,"Mercury Decide":0.012431651927976692,"Cloudflare Clef":0.1519,"cloudflare/clef-flash":0.2097,"cloudflare/clef-omni":0.2681,"liquid/d1-ultra":0.19285324175035704,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.010410980262177261,"open/robojev-27b":null,"open/robojev-4b-v2":0.17977728828192718,"open/robojev-4b-v3@0.25":0.10669060051441193,"open/robojev-4b-v3@0.5":0.102380250911392,"open/robojev-4b-v3@0.75":0.1167256573155804,"open/robojev-4b-v3":0.1125237519028778,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.16887542324435542,"respan/span-02":0.14472963,"typesafe/jev-1.13":0.13,"JEV-27B-VL (10 frames)":0.16919016298148581,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.002044677734375}},{"suite":"unseen","id":"rbm-ood/mit_franka/bd5008fe-b0ff-4d7b-b994-b7435b756829","task":"Pick up the spoon and place it inside the cup","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"bd5008fe-b0ff-4d7b-b994-b7435b756829","predictions":{"RoboJev-27B":0.7602419512107835,"GPT-6 Astra":0.87,"GPT-6.1 Sol":0.12,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.45004357313423854,"TypeSafe Jev 1.14":0.59,"Perplexity Decider":0.5025605931540245,"Liquid D1":0.7981867825403176,"Mercury Decide":0.3775406617944891,"Cloudflare Clef":0.2851,"cloudflare/clef-flash":0.4697,"cloudflare/clef-omni":0.2339,"liquid/d1-ultra":0.3907210731786067,"open/intern-decision-4b":0.37709365395745764,"open/robojev-27b-v1@0.5":0.602679355334289,"open/robojev-27b":null,"open/robojev-4b-v2":0.010890344798324344,"open/robojev-4b-v3@0.25":0.4073334336280823,"open/robojev-4b-v3@0.5":0.102380250911392,"open/robojev-4b-v3@0.75":0.0458382546620802,"open/robojev-4b-v3":0.03505281632584716,"openai/gpt-6-luna-decisions":0.09,"perplexity/pplx-decider-flash-v1.2":0.44494158141391865,"respan/span-02":0.65206885,"typesafe/jev-1.13":0.65,"JEV-27B-VL (10 frames)":0.5806757683835654,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.02001953125}},{"suite":"unseen","id":"rbm-ood/mit_franka/be2f859c-f6ba-484b-9a72-3a95d41ceb08","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"be2f859c-f6ba-484b-9a72-3a95d41ceb08","predictions":{"RoboJev-27B":0.0015062098759483146,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.0024766559757883155,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.024052321613488775,"Liquid D1":0.1008786146206548,"Mercury Decide":0.001700722484171748,"Cloudflare Clef":0.2131,"cloudflare/clef-flash":0.1869,"cloudflare/clef-omni":0.1027,"liquid/d1-ultra":0.06209063679927145,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":7.676558443902757e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.007644678711335276,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.04343408155889982,"open/robojev-4b-v3@0.75":0.028975397327291364,"open/robojev-4b-v3":0.021788411170123766,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.15705199229469902,"respan/span-02":0.075724706,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.0017933283414772096,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.003173828125}},{"suite":"unseen","id":"rbm-ood/mit_franka/be9ee93f-cc2e-40b2-b99e-9aff261867a5","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"be9ee93f-cc2e-40b2-b99e-9aff261867a5","predictions":{"RoboJev-27B":0.26182967372823046,"GPT-6 Astra":0.18,"GPT-6.1 Sol":0.22,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.35764336731027874,"TypeSafe Jev 1.14":0.23,"Perplexity Decider":0.2687228481775904,"Liquid D1":0.939913354875362,"Mercury Decide":0.033085981248949035,"Cloudflare Clef":0.2629,"cloudflare/clef-flash":0.7288,"cloudflare/clef-omni":0.5923,"liquid/d1-ultra":0.15087378290385461,"open/intern-decision-4b":0.5624106420506467,"open/robojev-27b-v1@0.5":0.031990430903611304,"open/robojev-27b":null,"open/robojev-4b-v2":0.008730681628235537,"open/robojev-4b-v3@0.25":0.3775406777858734,"open/robojev-4b-v3@0.5":0.12199371684192196,"open/robojev-4b-v3@0.75":0.038631651048510164,"open/robojev-4b-v3":0.021788411170123766,"openai/gpt-6-luna-decisions":0.99,"perplexity/pplx-decider-flash-v1.2":0.7449498102006868,"respan/span-02":0.65766454,"typesafe/jev-1.13":0.32,"JEV-27B-VL (10 frames)":0.5172541704999047,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.044677734375}},{"suite":"unseen","id":"rbm-ood/mit_franka/bea540e6-0b6b-493b-a89c-048a6f6e8f68","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"bea540e6-0b6b-493b-a89c-048a6f6e8f68","predictions":{"RoboJev-27B":0.6867473648320065,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.14,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.9534272531522867,"TypeSafe Jev 1.14":0.66,"Perplexity Decider":0.9128552386447921,"Liquid D1":0.9875683520281681,"Mercury Decide":0.9959298614950907,"Cloudflare Clef":0.8292,"cloudflare/clef-flash":0.8874,"cloudflare/clef-omni":0.6171,"liquid/d1-ultra":0.6439102066122557,"open/intern-decision-4b":0.8879876242264044,"open/robojev-27b-v1@0.5":0.9754574462467747,"open/robojev-27b":null,"open/robojev-4b-v2":0.014187968059593464,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.8195287241994405,"open/robojev-4b-v3@0.75":0.21256653766057104,"open/robojev-4b-v3":0.12986262050809297,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.9398558555337917,"respan/span-02":0.88554895,"typesafe/jev-1.13":0.59,"JEV-27B-VL (10 frames)":0.896076804472618,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.7421875}},{"suite":"unseen","id":"rbm-ood/mit_franka/bf994e7d-3f4a-40c4-9da8-cd464d98f373","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"bf994e7d-3f4a-40c4-9da8-cd464d98f373","predictions":{"RoboJev-27B":0.5266233044796752,"GPT-6 Astra":0.78,"GPT-6.1 Sol":0.86,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.5037920441616045,"TypeSafe Jev 1.14":0.67,"Perplexity Decider":0.4321427227193685,"Liquid D1":0.29421497216298875,"Mercury Decide":0.7981867777396212,"Cloudflare Clef":0.2254,"cloudflare/clef-flash":0.289,"cloudflare/clef-omni":0.0593,"liquid/d1-ultra":0.4507950668241079,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.9109069815544126,"open/robojev-27b":null,"open/robojev-4b-v2":0.7001924251222287,"open/robojev-4b-v3@0.25":0.43782350420951843,"open/robojev-4b-v3@0.5":0.32658221149990796,"open/robojev-4b-v3@0.75":0.32865255101542173,"open/robojev-4b-v3":0.2732370005831141,"openai/gpt-6-luna-decisions":0.33,"perplexity/pplx-decider-flash-v1.2":0.42446300784290447,"respan/span-02":0.2463142,"typesafe/jev-1.13":0.41,"JEV-27B-VL (10 frames)":0.32795059016403344,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.146484375}},{"suite":"unseen","id":"rbm-ood/mit_franka/c0806df4-7289-4c26-be73-40b4a33b471b","task":"Fold the towel in half","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"c0806df4-7289-4c26-be73-40b4a33b471b","predictions":{"RoboJev-27B":0.41716174172220816,"GPT-6 Astra":0.1,"GPT-6.1 Sol":0.2,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.4235233470349467,"TypeSafe Jev 1.14":0.48,"Perplexity Decider":0.5121352678051326,"Liquid D1":0.7310585669110203,"Mercury Decide":0.18242551936144574,"Cloudflare Clef":0.3739,"cloudflare/clef-flash":0.4352,"cloudflare/clef-omni":0.3463,"liquid/d1-ultra":0.31220409188357706,"open/intern-decision-4b":0.34810523633137336,"open/robojev-27b-v1@0.5":0.20894384637644053,"open/robojev-27b":null,"open/robojev-4b-v2":0.3385768147857754,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.07585817666120565,"open/robojev-4b-v3@0.75":0.028975397327291364,"open/robojev-4b-v3":0.017606235547797083,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.4915400473362198,"respan/span-02":0.29203895,"typesafe/jev-1.13":0.46,"JEV-27B-VL (10 frames)":0.41227929037836136,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0025482177734375}},{"suite":"unseen","id":"rbm-ood/mit_franka/c11d0ab2-69f5-40df-8334-38efc65658c8","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"c11d0ab2-69f5-40df-8334-38efc65658c8","predictions":{"RoboJev-27B":0.744228235200984,"GPT-6 Astra":0.35,"GPT-6.1 Sol":0.3,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.8155221127723122,"TypeSafe Jev 1.14":0.6,"Perplexity Decider":0.6795609324781153,"Liquid D1":0.6513548511303336,"Mercury Decide":0.9465966734015935,"Cloudflare Clef":0.4108,"cloudflare/clef-flash":0.2267,"cloudflare/clef-omni":0.2643,"liquid/d1-ultra":0.7085938400082761,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.8952139239718938,"open/robojev-27b":null,"open/robojev-4b-v2":0.0025170615300917137,"open/robojev-4b-v3@0.25":0.13296423852443695,"open/robojev-4b-v3@0.5":0.22270012535630726,"open/robojev-4b-v3@0.75":0.1050005837572588,"open/robojev-4b-v3":0.05887058738679302,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.3313417686465706,"respan/span-02":0.15585661,"typesafe/jev-1.13":0.55,"JEV-27B-VL (10 frames)":0.8133426087403232,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.119140625}},{"suite":"unseen","id":"rbm-ood/mit_franka/c3938b4a-0d7a-4df2-82ab-397b201449dd","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"c3938b4a-0d7a-4df2-82ab-397b201449dd","predictions":{"RoboJev-27B":0.060760113123250546,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.017226678327699425,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.02919165370111771,"Liquid D1":0.8175744806385543,"Mercury Decide":0.008577484114850882,"Cloudflare Clef":0.4141,"cloudflare/clef-flash":0.1864,"cloudflare/clef-omni":0.1816,"liquid/d1-ultra":0.10691174077426517,"open/intern-decision-4b":0.43758935794935333,"open/robojev-27b-v1@0.5":0.003907878809626987,"open/robojev-27b":null,"open/robojev-4b-v2":0.01138187822152329,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.02612421708095358,"open/robojev-4b-v3@0.75":0.019292242704938834,"open/robojev-4b-v3":0.01958823717659324,"openai/gpt-6-luna-decisions":0.49,"perplexity/pplx-decider-flash-v1.2":0.3659241069245438,"respan/span-02":0.24064389,"typesafe/jev-1.13":0.38,"JEV-27B-VL (10 frames)":0.00753962883648051,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.053466796875}},{"suite":"unseen","id":"rbm-ood/mit_franka/c77fedd0-526f-40a8-9a00-fd24fb4f450c","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"c77fedd0-526f-40a8-9a00-fd24fb4f450c","predictions":{"RoboJev-27B":0.4350151908764195,"GPT-6 Astra":0.22,"GPT-6.1 Sol":0.12,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.5517452722634583,"TypeSafe Jev 1.14":0.35,"Perplexity Decider":0.43399739469082355,"Liquid D1":0.7310585903489892,"Mercury Decide":0.7981867729389246,"Cloudflare Clef":0.2848,"cloudflare/clef-flash":0.3389,"cloudflare/clef-omni":0.1673,"liquid/d1-ultra":0.17084220680574735,"open/intern-decision-4b":0.43758935794935333,"open/robojev-27b-v1@0.5":0.7552247069682666,"open/robojev-27b":null,"open/robojev-4b-v2":0.7001924251222287,"open/robojev-4b-v3@0.25":0.7057850360870361,"open/robojev-4b-v3@0.5":0.37137657841700994,"open/robojev-4b-v3@0.75":0.2551315034592856,"open/robojev-4b-v3":0.1792055554427502,"openai/gpt-6-luna-decisions":0.11,"perplexity/pplx-decider-flash-v1.2":0.525137194922599,"respan/span-02":0.17137922,"typesafe/jev-1.13":0.39,"JEV-27B-VL (10 frames)":0.299882354834836,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.271484375}},{"suite":"unseen","id":"rbm-ood/mit_franka/c7cfb350-f106-49f6-a3b5-ab0799faaf08","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"c7cfb350-f106-49f6-a3b5-ab0799faaf08","predictions":{"RoboJev-27B":0.36299262901511997,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.89,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.3298544683989705,"TypeSafe Jev 1.14":0.58,"Perplexity Decider":0.23606078319366502,"Liquid D1":0.8354835289107309,"Mercury Decide":0.14804719239327382,"Cloudflare Clef":0.3207,"cloudflare/clef-flash":0.2994,"cloudflare/clef-omni":0.1651,"liquid/d1-ultra":0.46304398699442306,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.24483826943628192,"open/robojev-27b":null,"open/robojev-4b-v2":0.7772998717278379,"open/robojev-4b-v3@0.25":0.22270014882087708,"open/robojev-4b-v3@0.5":0.07585817666120565,"open/robojev-4b-v3@0.75":0.02167836395087896,"open/robojev-4b-v3":0.009760866998496955,"openai/gpt-6-luna-decisions":0.27,"perplexity/pplx-decider-flash-v1.2":0.33743376707527906,"respan/span-02":0.7507123,"typesafe/jev-1.13":0.41,"JEV-27B-VL (10 frames)":0.3861229640304066,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0203857421875}},{"suite":"unseen","id":"rbm-ood/mit_franka/caf3847b-517e-4255-84e5-55fb56530f14","task":"Pull a tissue from the tissue box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"caf3847b-517e-4255-84e5-55fb56530f14","predictions":{"RoboJev-27B":0.10565231788545455,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.06,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.22572726966538817,"TypeSafe Jev 1.14":0.07,"Perplexity Decider":0.04677606535475016,"Liquid D1":0.8175744761936437,"Mercury Decide":0.007577242458436242,"Cloudflare Clef":0.2843,"cloudflare/clef-flash":0.4671,"cloudflare/clef-omni":0.5047,"liquid/d1-ultra":0.5492049331758921,"open/intern-decision-4b":0.36247442200877295,"open/robojev-27b-v1@0.5":0.018563209408861428,"open/robojev-27b":null,"open/robojev-4b-v2":0.9357502880950697,"open/robojev-4b-v3@0.25":0.531209409236908,"open/robojev-4b-v3@0.5":0.8095931022908179,"open/robojev-4b-v3@0.75":0.8245695962243903,"open/robojev-4b-v3":0.828649621504827,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2876804518379052,"respan/span-02":0.13231844,"typesafe/jev-1.13":0.27,"JEV-27B-VL (10 frames)":0.09812117290423858,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.004913330078125}},{"suite":"unseen","id":"rbm-ood/mit_franka/cbea2c79-7d49-46c8-87de-cb8eddd5360e","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"cbea2c79-7d49-46c8-87de-cb8eddd5360e","predictions":{"RoboJev-27B":0.005336994715199233,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.016275475375641106,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.019345927119228692,"Liquid D1":0.1259227582746744,"Mercury Decide":0.003172683163535608,"Cloudflare Clef":0.2748,"cloudflare/clef-flash":0.2992,"cloudflare/clef-omni":0.2226,"liquid/d1-ultra":0.10228895895750384,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":5.3898389643064854e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.006996270681650968,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.017755273617510888,"open/robojev-4b-v3@0.75":0.012802394334981567,"open/robojev-4b-v3":0.016690455215260983,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1539480360100895,"respan/span-02":0.27980837,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.0062338441731371865,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000804901123046875}},{"suite":"unseen","id":"rbm-ood/mit_franka/ccb4bc2e-7531-4c0a-b007-62967a77628d","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"ccb4bc2e-7531-4c0a-b007-62967a77628d","predictions":{"RoboJev-27B":0.11654227618898928,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.5153406814864652,"TypeSafe Jev 1.14":0.23,"Perplexity Decider":0.15644201680203226,"Liquid D1":0.6791787121629466,"Mercury Decide":0.13296422989056964,"Cloudflare Clef":0.6832,"cloudflare/clef-flash":0.2509,"cloudflare/clef-omni":0.2392,"liquid/d1-ultra":0.20868887757980986,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.828071710483547,"open/robojev-27b":null,"open/robojev-4b-v2":0.004293165515526464,"open/robojev-4b-v3@0.25":0.22270014882087708,"open/robojev-4b-v3@0.5":0.1368024864039654,"open/robojev-4b-v3@0.75":0.12300397579729967,"open/robojev-4b-v3":0.1125237519028778,"openai/gpt-6-luna-decisions":0.78,"perplexity/pplx-decider-flash-v1.2":0.46645727771022855,"respan/span-02":0.11416101,"typesafe/jev-1.13":0.26,"JEV-27B-VL (10 frames)":0.04434348524433343,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01068115234375}},{"suite":"unseen","id":"rbm-ood/mit_franka/cdbebfe5-2858-49e1-b807-e88935c2f003","task":"Pull a tissue from the tissue box","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"cdbebfe5-2858-49e1-b807-e88935c2f003","predictions":{"RoboJev-27B":0.928726747677065,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.82,"JEV-27B-VL":0.8630199622234798,"TypeSafe Jev 1.14":0.76,"Perplexity Decider":0.885156814510391,"Liquid D1":0.9525741298517642,"Mercury Decide":0.9626731105140616,"Cloudflare Clef":0.8994,"cloudflare/clef-flash":0.781,"cloudflare/clef-omni":0.8411,"liquid/d1-ultra":0.8882825553746903,"open/intern-decision-4b":0.6229063460425425,"open/robojev-27b-v1@0.5":0.9881372172116967,"open/robojev-27b":null,"open/robojev-4b-v2":0.9920090979300479,"open/robojev-4b-v3@0.25":0.9399133324623108,"open/robojev-4b-v3@0.5":0.9537489247538957,"open/robojev-4b-v3@0.75":0.9004631151043695,"open/robojev-4b-v3":0.8207944445572498,"openai/gpt-6-luna-decisions":0.91,"perplexity/pplx-decider-flash-v1.2":0.7963775390147603,"respan/span-02":0.8721626,"typesafe/jev-1.13":0.84,"JEV-27B-VL (10 frames)":0.8740568097227521,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.54296875}},{"suite":"unseen","id":"rbm-ood/mit_franka/cee4e79a-6cf1-4981-b500-d68ac80c51a2","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"cee4e79a-6cf1-4981-b500-d68ac80c51a2","predictions":{"RoboJev-27B":0.7507916544894804,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.5153406814864652,"TypeSafe Jev 1.14":0.51,"Perplexity Decider":0.36307549852379095,"Liquid D1":0.8933093975331751,"Mercury Decide":0.4378234991142019,"Cloudflare Clef":0.5591,"cloudflare/clef-flash":0.7742,"cloudflare/clef-omni":0.0882,"liquid/d1-ultra":0.3122040716652746,"open/intern-decision-4b":0.7439389554145914,"open/robojev-27b-v1@0.5":0.35589313430615216,"open/robojev-27b":null,"open/robojev-4b-v2":0.003007688028932422,"open/robojev-4b-v3@0.25":0.9626730680465698,"open/robojev-4b-v3@0.5":0.48355855873161024,"open/robojev-4b-v3@0.75":0.1669856712343507,"open/robojev-4b-v3":0.0721349360304201,"openai/gpt-6-luna-decisions":0.51,"perplexity/pplx-decider-flash-v1.2":0.8295189750673344,"respan/span-02":0.4828884,"typesafe/jev-1.13":0.5,"JEV-27B-VL (10 frames)":0.6244167153078108,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0038299560546875}},{"suite":"unseen","id":"rbm-ood/mit_franka/cf424626-1422-47bd-b676-19a75413d057","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"cf424626-1422-47bd-b676-19a75413d057","predictions":{"RoboJev-27B":0.5975330648757858,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.6717418137353136,"TypeSafe Jev 1.14":0.59,"Perplexity Decider":0.8680925407083647,"Liquid D1":0.8933094145755219,"Mercury Decide":0.8354835411997897,"Cloudflare Clef":0.5991,"cloudflare/clef-flash":0.2204,"cloudflare/clef-omni":0.4004,"liquid/d1-ultra":0.6770987087182544,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.45516550866554595,"open/robojev-27b":null,"open/robojev-4b-v2":0.09306389901723976,"open/robojev-4b-v3@0.25":0.13296423852443695,"open/robojev-4b-v3@0.5":0.09649050143553403,"open/robojev-4b-v3@0.75":0.048513171421607396,"open/robojev-4b-v3":0.03505281632584716,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.7890788214296383,"respan/span-02":0.3421684,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.7724811436871893,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00689697265625}},{"suite":"unseen","id":"rbm-ood/mit_franka/cf62479b-dec8-4b56-903d-9c66cf82e972","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"cf62479b-dec8-4b56-903d-9c66cf82e972","predictions":{"RoboJev-27B":0.5727517209698245,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.8497665318362629,"TypeSafe Jev 1.14":0.73,"Perplexity Decider":0.8251774441215095,"Liquid D1":0.9924227596845995,"Mercury Decide":0.8933093954028817,"Cloudflare Clef":0.8874,"cloudflare/clef-flash":0.8888,"cloudflare/clef-omni":0.7754,"liquid/d1-ultra":0.6551469213552649,"open/intern-decision-4b":0.8940776460411956,"open/robojev-27b-v1@0.5":0.8572376524087991,"open/robojev-27b":null,"open/robojev-4b-v2":0.005858834000676852,"open/robojev-4b-v3@0.25":0.9820137619972229,"open/robojev-4b-v3@0.5":0.8381784546520696,"open/robojev-4b-v3@0.75":0.41165138407414853,"open/robojev-4b-v3":0.2841612815794545,"openai/gpt-6-luna-decisions":0.85,"perplexity/pplx-decider-flash-v1.2":0.9033506741631838,"respan/span-02":0.7971561,"typesafe/jev-1.13":0.81,"JEV-27B-VL (10 frames)":0.8798060323222988,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2353515625}},{"suite":"unseen","id":"rbm-ood/mit_franka/cfb656ed-cbff-4438-bf36-7193a2658da4","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"cfb656ed-cbff-4438-bf36-7193a2658da4","predictions":{"RoboJev-27B":0.3419330485478976,"GPT-6 Astra":0.18,"GPT-6.1 Sol":0.3,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.5838657458401092,"TypeSafe Jev 1.14":0.22,"Perplexity Decider":0.5674584509025656,"Liquid D1":0.972414719172208,"Mercury Decide":0.5,"Cloudflare Clef":0.7908,"cloudflare/clef-flash":0.7695,"cloudflare/clef-omni":0.1898,"liquid/d1-ultra":0.3122040817744257,"open/intern-decision-4b":0.8527907640733415,"open/robojev-27b-v1@0.5":0.14227420444839914,"open/robojev-27b":null,"open/robojev-4b-v2":0.007990902069952163,"open/robojev-4b-v3@0.25":0.8807970285415649,"open/robojev-4b-v3@0.5":0.21151967170194583,"open/robojev-4b-v3@0.75":0.12300397579729967,"open/robojev-4b-v3":0.06858087544025289,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.41138841924976477,"respan/span-02":0.15893233,"typesafe/jev-1.13":0.29,"JEV-27B-VL (10 frames)":0.5595398439924019,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00445556640625}},{"suite":"unseen","id":"rbm-ood/mit_franka/cfe4bd76-ee6c-4366-8ed4-eb4788426005","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"cfe4bd76-ee6c-4366-8ed4-eb4788426005","predictions":{"RoboJev-27B":0.5562908548520973,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.33498214143776517,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.13048162456909065,"Liquid D1":0.7549149868676283,"Mercury Decide":0.3486451285660856,"Cloudflare Clef":0.8546,"cloudflare/clef-flash":0.6031,"cloudflare/clef-omni":0.4049,"liquid/d1-ultra":0.20868887757980986,"open/intern-decision-4b":0.6659927647326706,"open/robojev-27b-v1@0.5":0.6662712055735479,"open/robojev-27b":null,"open/robojev-4b-v2":0.01138187822152329,"open/robojev-4b-v3@0.25":0.8933094143867493,"open/robojev-4b-v3@0.5":0.24630430768454536,"open/robojev-4b-v3@0.75":0.45547541541136,"open/robojev-4b-v3":0.6696321275705963,"openai/gpt-6-luna-decisions":0.82,"perplexity/pplx-decider-flash-v1.2":0.47007636253503965,"respan/span-02":0.33454868,"typesafe/jev-1.13":0.33,"JEV-27B-VL (10 frames)":0.38728918000034257,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0439453125}},{"suite":"unseen","id":"rbm-ood/mit_franka/d0753448-c525-4e1b-a96c-4738772cb980","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"d0753448-c525-4e1b-a96c-4738772cb980","predictions":{"RoboJev-27B":0.5360201248707773,"GPT-6 Astra":0.8,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.35,"JEV-27B-VL":0.5268729585790383,"TypeSafe Jev 1.14":0.52,"Perplexity Decider":0.5390576281750626,"Liquid D1":0.880797081106935,"Mercury Decide":0.7981867777396212,"Cloudflare Clef":0.3078,"cloudflare/clef-flash":0.2141,"cloudflare/clef-omni":0.1855,"liquid/d1-ultra":0.6551469000827254,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.42400416650457107,"open/robojev-27b":null,"open/robojev-4b-v2":0.10927050321483402,"open/robojev-4b-v3@0.25":0.3208213150501251,"open/robojev-4b-v3@0.5":0.25872010509521604,"open/robojev-4b-v3@0.75":0.19332136802205585,"open/robojev-4b-v3":0.1125237519028778,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.6711142973809989,"respan/span-02":0.22729786,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.6506897948058601,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.6015625}},{"suite":"unseen","id":"rbm-ood/mit_franka/d08f2b68-4269-4b2b-bd78-c400099f2fae","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"d08f2b68-4269-4b2b-bd78-c400099f2fae","predictions":{"RoboJev-27B":0.7601290158368166,"GPT-6 Astra":0.16,"GPT-6.1 Sol":0.22,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.8084678840720323,"TypeSafe Jev 1.14":0.49,"Perplexity Decider":0.7223231591735889,"Liquid D1":0.9324533163686646,"Mercury Decide":0.9241418278134569,"Cloudflare Clef":0.5037,"cloudflare/clef-flash":0.5187,"cloudflare/clef-omni":0.4678,"liquid/d1-ultra":0.5246623165651004,"open/intern-decision-4b":0.7439389554145914,"open/robojev-27b-v1@0.5":0.8915543312029467,"open/robojev-27b":null,"open/robojev-4b-v2":0.007990902069952163,"open/robojev-4b-v3@0.25":0.8933094143867493,"open/robojev-4b-v3@0.5":0.5,"open/robojev-4b-v3@0.75":0.20277377238617383,"open/robojev-4b-v3":0.12384396710192513,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.6803205281585066,"respan/span-02":0.87584853,"typesafe/jev-1.13":0.63,"JEV-27B-VL (10 frames)":0.8745598523840807,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.373046875}},{"suite":"unseen","id":"rbm-ood/mit_franka/d0fce1a9-ea9e-4013-bcf7-85c9f9255f2d","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"d0fce1a9-ea9e-4013-bcf7-85c9f9255f2d","predictions":{"RoboJev-27B":0.42297878217788226,"GPT-6 Astra":0.45,"GPT-6.1 Sol":0.8,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.635138743080919,"TypeSafe Jev 1.14":0.55,"Perplexity Decider":0.7380371373986109,"Liquid D1":0.9830850830164469,"Mercury Decide":0.9046505395995929,"Cloudflare Clef":0.6161,"cloudflare/clef-flash":0.699,"cloudflare/clef-omni":0.1408,"liquid/d1-ultra":0.5492049215204136,"open/intern-decision-4b":0.6518947636686268,"open/robojev-27b-v1@0.5":0.5088126025966875,"open/robojev-27b":null,"open/robojev-4b-v2":0.009969411693719354,"open/robojev-4b-v3@0.25":0.9626730680465698,"open/robojev-4b-v3@0.5":0.741279894904784,"open/robojev-4b-v3@0.75":0.2666072781234324,"open/robojev-4b-v3":0.21343419258585974,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.8651305281832264,"respan/span-02":0.14095607,"typesafe/jev-1.13":0.59,"JEV-27B-VL (10 frames)":0.6032173196908487,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01544189453125}},{"suite":"unseen","id":"rbm-ood/mit_franka/d12139fb-0bea-46b1-abfd-0dc23e000fa5","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"d12139fb-0bea-46b1-abfd-0dc23e000fa5","predictions":{"RoboJev-27B":0.7276668945067264,"GPT-6 Astra":0.82,"GPT-6.1 Sol":0.76,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.4576800881477885,"TypeSafe Jev 1.14":0.48,"Perplexity Decider":0.39048582454389347,"Liquid D1":0.679178699175393,"Mercury Decide":0.4378234991142019,"Cloudflare Clef":0.2924,"cloudflare/clef-flash":0.4408,"cloudflare/clef-omni":0.2045,"liquid/d1-ultra":0.5492049215204136,"open/intern-decision-4b":0.43758935794935333,"open/robojev-27b-v1@0.5":0.7007800813466591,"open/robojev-27b":null,"open/robojev-4b-v2":0.2998075748777713,"open/robojev-4b-v3@0.25":0.8670357465744019,"open/robojev-4b-v3@0.5":0.9090947575586418,"open/robojev-4b-v3@0.75":0.8066786319779442,"open/robojev-4b-v3":0.13612834674424493,"openai/gpt-6-luna-decisions":0.18,"perplexity/pplx-decider-flash-v1.2":0.7307877370766784,"respan/span-02":0.7354623,"typesafe/jev-1.13":0.66,"JEV-27B-VL (10 frames)":0.42975055119198946,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01324462890625}},{"suite":"unseen","id":"rbm-ood/mit_franka/d2130229-c90e-4f99-89a8-708ee3d7d40c","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"d2130229-c90e-4f99-89a8-708ee3d7d40c","predictions":{"RoboJev-27B":0.028088641598218445,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.1342164145712244,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.04373513221609743,"Liquid D1":0.08509904500702024,"Mercury Decide":0.020332354047595494,"Cloudflare Clef":0.2329,"cloudflare/clef-flash":0.2348,"cloudflare/clef-omni":0.1096,"liquid/d1-ultra":0.09357237981851457,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.007910246952689562,"open/robojev-27b":null,"open/robojev-4b-v2":0.003007688028932422,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.011276606158891207,"open/robojev-4b-v3@0.75":0.006308531582070822,"open/robojev-4b-v3":0.0041144364846599805,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.08991736373074954,"respan/span-02":0.02848698,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.05238836716332499,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00689697265625}},{"suite":"unseen","id":"rbm-ood/mit_franka/d2d0d2e1-536c-4ea7-888f-fa5745aae2d1","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"d2d0d2e1-536c-4ea7-888f-fa5745aae2d1","predictions":{"RoboJev-27B":0.00601810572571435,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.003271728416321254,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.016409834760308443,"Liquid D1":0.18242552380635632,"Mercury Decide":0.0009110510197724983,"Cloudflare Clef":0.1052,"cloudflare/clef-flash":0.2276,"cloudflare/clef-omni":0.1532,"liquid/d1-ultra":0.10228895895750384,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":5.327740243926886e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.0034372413231743533,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.03372324040197287,"open/robojev-4b-v3@0.75":0.03444519627897428,"open/robojev-4b-v3":0.04319701644612397,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.173132238187895,"respan/span-02":0.07869395,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.0051462089821312,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.004913330078125}},{"suite":"unseen","id":"rbm-ood/mit_franka/d4b21264-5347-43db-99a0-1aa67d59dae2","task":"Pick up the spoon and place it inside the cup","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"d4b21264-5347-43db-99a0-1aa67d59dae2","predictions":{"RoboJev-27B":0.004770068151608218,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.010119928625804102,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.016354949723972324,"Liquid D1":0.28140560742914383,"Mercury Decide":0.0028009270139436556,"Cloudflare Clef":0.1768,"cloudflare/clef-flash":0.2132,"cloudflare/clef-omni":0.1108,"liquid/d1-ultra":0.10691173515542983,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.001928259725566028,"open/robojev-27b":null,"open/robojev-4b-v2":0.001233791749980779,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.013703364243695216,"open/robojev-4b-v3@0.75":0.007532610956861541,"open/robojev-4b-v3":0.007064018099624773,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.14607880060573908,"respan/span-02":0.15257843,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.008018701986229178,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00421142578125}},{"suite":"unseen","id":"rbm-ood/mit_franka/d4bd0b33-6be2-4276-be13-28861e9ef0ee","task":"Pour the pebbles from the cup onto the plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"d4bd0b33-6be2-4276-be13-28861e9ef0ee","predictions":{"RoboJev-27B":0.27928799834163903,"GPT-6 Astra":0.06,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.2112642834425615,"TypeSafe Jev 1.14":0.11,"Perplexity Decider":0.1103027200789171,"Liquid D1":0.7772998560157665,"Mercury Decide":0.029312230751356316,"Cloudflare Clef":0.327,"cloudflare/clef-flash":0.4986,"cloudflare/clef-omni":0.2013,"liquid/d1-ultra":0.2914061599917239,"open/intern-decision-4b":0.5624106420506467,"open/robojev-27b-v1@0.5":0.1150226041258526,"open/robojev-27b":null,"open/robojev-4b-v2":0.027346786441616523,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.4345875784292984,"open/robojev-4b-v3@0.75":0.06792255924998467,"open/robojev-4b-v3":0.04319701644612397,"openai/gpt-6-luna-decisions":0.37,"perplexity/pplx-decider-flash-v1.2":0.36599823722441993,"respan/span-02":0.8549723,"typesafe/jev-1.13":0.41,"JEV-27B-VL (10 frames)":0.060962529495531784,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.03515625}},{"suite":"unseen","id":"rbm-ood/mit_franka/d929ea18-4f95-4015-8804-919dd091c626","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"d929ea18-4f95-4015-8804-919dd091c626","predictions":{"RoboJev-27B":0.6908929558595562,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.12,"Claude Opus 5.5":0.25,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.8012096529779148,"TypeSafe Jev 1.14":0.76,"Perplexity Decider":0.8689652360108803,"Liquid D1":0.9796676485866417,"Mercury Decide":0.9706877660687704,"Cloudflare Clef":0.6222,"cloudflare/clef-flash":0.8529,"cloudflare/clef-omni":0.6507,"liquid/d1-ultra":0.6439101958177847,"open/intern-decision-4b":0.7439389554145914,"open/robojev-27b-v1@0.5":0.9160523841723828,"open/robojev-27b":null,"open/robojev-4b-v2":0.09690095299759889,"open/robojev-4b-v3@0.25":0.970687747001648,"open/robojev-4b-v3@0.5":0.9193991005705059,"open/robojev-4b-v3@0.75":0.18420778945962635,"open/robojev-4b-v3":0.07585818271507015,"openai/gpt-6-luna-decisions":0.85,"perplexity/pplx-decider-flash-v1.2":0.9322080363240656,"respan/span-02":0.81983876,"typesafe/jev-1.13":0.77,"JEV-27B-VL (10 frames)":0.8725474693287266,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.12353515625}},{"suite":"unseen","id":"rbm-ood/mit_franka/d92c5b5a-f552-4d0b-be41-091a5525149f","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"d92c5b5a-f552-4d0b-be41-091a5525149f","predictions":{"RoboJev-27B":0.5462601011547754,"GPT-6 Astra":0.87,"GPT-6.1 Sol":0.86,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.47300936358935247,"TypeSafe Jev 1.14":0.19,"Perplexity Decider":0.5493644020045088,"Liquid D1":0.8933093975331751,"Mercury Decide":0.651354857898194,"Cloudflare Clef":0.1583,"cloudflare/clef-flash":0.6495,"cloudflare/clef-omni":0.3509,"liquid/d1-ultra":0.2714469285488543,"open/intern-decision-4b":0.6932998143038492,"open/robojev-27b-v1@0.5":0.18384177714759564,"open/robojev-27b":null,"open/robojev-4b-v2":0.003007688028932422,"open/robojev-4b-v3@0.25":0.9241418242454529,"open/robojev-4b-v3@0.5":0.1804712758005596,"open/robojev-4b-v3@0.75":0.1754304037756096,"open/robojev-4b-v3":0.14942342283990945,"openai/gpt-6-luna-decisions":0.74,"perplexity/pplx-decider-flash-v1.2":0.5091633072592701,"respan/span-02":0.549812,"typesafe/jev-1.13":0.35,"JEV-27B-VL (10 frames)":0.6807866090773449,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.040771484375}},{"suite":"unseen","id":"rbm-ood/mit_franka/dd34d3ce-3758-4543-8bd1-c10135b46e71","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"dd34d3ce-3758-4543-8bd1-c10135b46e71","predictions":{"RoboJev-27B":0.7002349703113788,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.377333288902431,"TypeSafe Jev 1.14":0.65,"Perplexity Decider":0.40788399436587824,"Liquid D1":0.9324533112067127,"Mercury Decide":0.6224593312018546,"Cloudflare Clef":0.3276,"cloudflare/clef-flash":0.243,"cloudflare/clef-omni":0.0903,"liquid/d1-ultra":0.6439101958177847,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.9051413866938001,"open/robojev-27b":null,"open/robojev-4b-v2":0.8991213731853014,"open/robojev-4b-v3@0.25":0.9399133324623108,"open/robojev-4b-v3@0.5":0.9703110587107732,"open/robojev-4b-v3@0.75":0.9514868285783926,"open/robojev-4b-v3":0.881933594679255,"openai/gpt-6-luna-decisions":0.85,"perplexity/pplx-decider-flash-v1.2":0.7697619174423677,"respan/span-02":0.21630643,"typesafe/jev-1.13":0.68,"JEV-27B-VL (10 frames)":0.5837620410518095,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.52734375}},{"suite":"unseen","id":"rbm-ood/mit_franka/dfe31e07-ba00-418e-bc78-8fd67141fce2","task":"Pick up the mouse and place it right next to the laptop, while avoiding spilling coffee","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"dfe31e07-ba00-418e-bc78-8fd67141fce2","predictions":{"RoboJev-27B":0.037059155263050036,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":0.07244783814257592,"TypeSafe Jev 1.14":0.37,"Perplexity Decider":0.036958049149321534,"Liquid D1":0.13296423676207594,"Mercury Decide":0.00970847811109164,"Cloudflare Clef":0.2161,"cloudflare/clef-flash":0.2651,"cloudflare/clef-omni":0.2116,"liquid/d1-ultra":0.05658366274976866,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.005341114704923603,"open/robojev-27b":null,"open/robojev-4b-v2":0.0025170615300917137,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.017755273617510888,"open/robojev-4b-v3@0.75":0.008476838215708002,"open/robojev-4b-v3":0.0053922199218183735,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2712098478895904,"respan/span-02":0.11870079,"typesafe/jev-1.13":0.13,"JEV-27B-VL (10 frames)":0.07572832979461165,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0021209716796875}},{"suite":"unseen","id":"rbm-ood/mit_franka/e25bd65b-1441-4803-8bd0-266526d4396b","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"e25bd65b-1441-4803-8bd0-266526d4396b","predictions":{"RoboJev-27B":0.8745477665910485,"GPT-6 Astra":0.91,"GPT-6.1 Sol":0.92,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.7504823234709124,"TypeSafe Jev 1.14":0.57,"Perplexity Decider":0.819049509711535,"Liquid D1":0.2814056194821861,"Mercury Decide":0.9525741222784364,"Cloudflare Clef":0.2219,"cloudflare/clef-flash":0.1241,"cloudflare/clef-omni":0.0482,"liquid/d1-ultra":0.5123386675987678,"open/intern-decision-4b":0.10012611628383591,"open/robojev-27b-v1@0.5":0.6881511256800669,"open/robojev-27b":null,"open/robojev-4b-v2":0.014826107129937436,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.02154587702420825,"open/robojev-4b-v3@0.75":0.02167836395087896,"open/robojev-4b-v3":0.018571313779720225,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.7447832537414396,"respan/span-02":0.087145336,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.8187378005046204,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.162109375}},{"suite":"unseen","id":"rbm-ood/mit_franka/e28c2548-9b6e-40c6-b813-00dd8cfe63ad","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"e28c2548-9b6e-40c6-b813-00dd8cfe63ad","predictions":{"RoboJev-27B":0.9835697755732514,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.75,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.9653481484810673,"TypeSafe Jev 1.14":0.8,"Perplexity Decider":0.9743940696726127,"Liquid D1":0.9783846661343925,"Mercury Decide":0.9525741258126562,"Cloudflare Clef":0.7298,"cloudflare/clef-flash":0.2736,"cloudflare/clef-omni":0.289,"liquid/d1-ultra":0.8727197425231619,"open/intern-decision-4b":0.5624106420506467,"open/robojev-27b-v1@0.5":0.9938238687427775,"open/robojev-27b":null,"open/robojev-4b-v2":0.003593602817215226,"open/robojev-4b-v3@0.25":0.9740425944328308,"open/robojev-4b-v3@0.5":0.9683560447201516,"open/robojev-4b-v3@0.75":0.9635193115978655,"open/robojev-4b-v3":0.9241418172849298,"openai/gpt-6-luna-decisions":0.08,"perplexity/pplx-decider-flash-v1.2":0.9380051643211954,"respan/span-02":0.19602378,"typesafe/jev-1.13":0.47,"JEV-27B-VL (10 frames)":0.9588821085322115,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.578125}},{"suite":"unseen","id":"rbm-ood/mit_franka/e44b42ab-b1cc-44c3-aea0-8361c7cc29fa","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"e44b42ab-b1cc-44c3-aea0-8361c7cc29fa","predictions":{"RoboJev-27B":0.02510382374473388,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.033745904968570745,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.027326241816675256,"Liquid D1":0.17328820592932656,"Mercury Decide":0.005911068867188938,"Cloudflare Clef":0.1708,"cloudflare/clef-flash":0.2703,"cloudflare/clef-omni":0.2144,"liquid/d1-ultra":0.09784417419445134,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.004289776503477303,"open/robojev-27b":null,"open/robojev-4b-v2":0.0022022489536237186,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.006269376036423619,"open/robojev-4b-v3@0.75":0.003927901618504033,"open/robojev-4b-v3":0.002816147667248498,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.11179975681478312,"respan/span-02":0.25907803,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.0236185371838358,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.4140625}},{"suite":"unseen","id":"rbm-ood/mit_franka/e495eabb-9540-4cf3-a8ed-f850a7c4d979","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"e495eabb-9540-4cf3-a8ed-f850a7c4d979","predictions":{"RoboJev-27B":0.8700440204747572,"GPT-6 Astra":0.3,"GPT-6.1 Sol":0.18,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.7999800472461611,"TypeSafe Jev 1.14":0.67,"Perplexity Decider":0.7724217127064043,"Liquid D1":0.9525741261492485,"Mercury Decide":0.914900948612085,"Cloudflare Clef":0.7483,"cloudflare/clef-flash":0.5828,"cloudflare/clef-omni":0.6212,"liquid/d1-ultra":0.7285530807614236,"open/intern-decision-4b":0.7318060856600669,"open/robojev-27b-v1@0.5":0.8824445712800915,"open/robojev-27b":null,"open/robojev-4b-v2":0.00731334505501762,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.21151967170194583,"open/robojev-4b-v3@0.75":0.1107273107211166,"open/robojev-4b-v3":0.08383818708105521,"openai/gpt-6-luna-decisions":0.86,"perplexity/pplx-decider-flash-v1.2":0.6368106957953127,"respan/span-02":0.8169812,"typesafe/jev-1.13":0.84,"JEV-27B-VL (10 frames)":0.8455104835120769,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.291015625}},{"suite":"unseen","id":"rbm-ood/mit_franka/e55a6b32-2e81-47fd-bf93-7d455f587f8d","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"e55a6b32-2e81-47fd-bf93-7d455f587f8d","predictions":{"RoboJev-27B":0.17891932213667247,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.62,"Claude Sonnet 5.5":0.45,"JEV-27B-VL":0.1173024821565874,"TypeSafe Jev 1.14":0.59,"Perplexity Decider":0.16445027652803498,"Liquid D1":0.3775406547908327,"Mercury Decide":0.017986212923033665,"Cloudflare Clef":0.2324,"cloudflare/clef-flash":0.3188,"cloudflare/clef-omni":0.0989,"liquid/d1-ultra":0.333787150806788,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.014043253038755282,"open/robojev-27b":null,"open/robojev-4b-v2":0.8066786264852919,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.03828411009766295,"open/robojev-4b-v3@0.75":0.010731211960485985,"open/robojev-4b-v3":0.0074556149068047885,"openai/gpt-6-luna-decisions":0.19,"perplexity/pplx-decider-flash-v1.2":0.2533546432656199,"respan/span-02":0.77199805,"typesafe/jev-1.13":0.19,"JEV-27B-VL (10 frames)":0.2768850190410822,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.341796875}},{"suite":"unseen","id":"rbm-ood/mit_franka/e8ff0eff-9796-4374-9502-94d54ff54835","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"e8ff0eff-9796-4374-9502-94d54ff54835","predictions":{"RoboJev-27B":0.1857968804207659,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.4922393591953599,"TypeSafe Jev 1.14":0.33,"Perplexity Decider":0.24752388318128032,"Liquid D1":0.9399133523506772,"Mercury Decide":0.24508501864634827,"Cloudflare Clef":0.478,"cloudflare/clef-flash":0.35,"cloudflare/clef-omni":0.1482,"liquid/d1-ultra":0.1708422101401565,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.043978048310295094,"open/robojev-27b":null,"open/robojev-4b-v2":0.005361080321059209,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.04343408155889982,"open/robojev-4b-v3@0.75":0.02167836395087896,"open/robojev-4b-v3":0.013473327870331066,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.5177561447756641,"respan/span-02":0.11351163,"typesafe/jev-1.13":0.34,"JEV-27B-VL (10 frames)":0.40778943511215354,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.03955078125}},{"suite":"unseen","id":"rbm-ood/mit_franka/ea0b24b3-a13d-4b1d-9fcb-4641918adde3","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"ea0b24b3-a13d-4b1d-9fcb-4641918adde3","predictions":{"RoboJev-27B":0.05980071898102256,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.061408392147026036,"TypeSafe Jev 1.14":0.24,"Perplexity Decider":0.08798856516592823,"Liquid D1":0.37754066879814546,"Mercury Decide":0.017986207955231072,"Cloudflare Clef":0.4515,"cloudflare/clef-flash":0.2802,"cloudflare/clef-omni":0.1408,"liquid/d1-ultra":0.2617952535625818,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.010137129355235232,"open/robojev-27b":null,"open/robojev-4b-v2":0.008730681628235537,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.022977370307335907,"open/robojev-4b-v3@0.75":0.018197691623827453,"open/robojev-4b-v3":0.017606235547797083,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.24461579079953444,"respan/span-02":0.20322809,"typesafe/jev-1.13":0.19,"JEV-27B-VL (10 frames)":0.07084585977483882,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0025482177734375}},{"suite":"unseen","id":"rbm-ood/mit_franka/eb51e61f-1866-4fb9-814a-12b2f5a44298","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"eb51e61f-1866-4fb9-814a-12b2f5a44298","predictions":{"RoboJev-27B":0.0013908720427170413,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0010836254439999934,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.019387094901278927,"Liquid D1":0.029312233295254994,"Mercury Decide":0.001032230802429997,"Cloudflare Clef":0.1264,"cloudflare/clef-flash":0.2167,"cloudflare/clef-omni":0.1113,"liquid/d1-ultra":0.030604420857057692,"open/intern-decision-4b":0.12511350509772579,"open/robojev-27b-v1@0.5":2.0932589398996113e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.0011285254845784295,"open/robojev-4b-v3@0.25":0.006692850962281227,"open/robojev-4b-v3@0.5":0.002197092076271529,"open/robojev-4b-v3@0.75":0.001271016248975737,"open/robojev-4b-v3":0.0009012109819517691,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.03444052814018267,"respan/span-02":0.34047526,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.005796461467083705,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000732421875}},{"suite":"unseen","id":"rbm-ood/mit_franka/ebdcb9c5-a3c8-4de7-bf1c-d5e27472ef6a","task":"Pick up the spatula and stir the beans in the pot","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"ebdcb9c5-a3c8-4de7-bf1c-d5e27472ef6a","predictions":{"RoboJev-27B":0.019562991349755726,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.0468948478651186,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.059842376644686,"Liquid D1":0.06008665017400762,"Mercury Decide":0.01798620769203627,"Cloudflare Clef":0.4295,"cloudflare/clef-flash":0.2201,"cloudflare/clef-omni":0.0961,"liquid/d1-ultra":0.3017033476471517,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.0012569495689263041,"open/robojev-27b":null,"open/robojev-4b-v2":0.1381957315129781,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.03828411009766295,"open/robojev-4b-v3@0.75":0.038631651048510164,"open/robojev-4b-v3":0.03155642361885442,"openai/gpt-6-luna-decisions":0.1,"perplexity/pplx-decider-flash-v1.2":0.13769533002142684,"respan/span-02":0.06316943,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.04724495428863044,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006683349609375}},{"suite":"unseen","id":"rbm-ood/mit_franka/ec5cc6e4-1e92-4d88-8a88-9b82a40f51ce","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"ec5cc6e4-1e92-4d88-8a88-9b82a40f51ce","predictions":{"RoboJev-27B":0.19033223446137182,"GPT-6 Astra":0.87,"GPT-6.1 Sol":0.86,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.07,"JEV-27B-VL":0.32815409860942907,"TypeSafe Jev 1.14":0.18,"Perplexity Decider":0.23925403903926545,"Liquid D1":0.4073334000459302,"Mercury Decide":0.24508501864634827,"Cloudflare Clef":0.1761,"cloudflare/clef-flash":0.3112,"cloudflare/clef-omni":0.1522,"liquid/d1-ultra":0.3229013015746585,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.24123534450085365,"open/robojev-27b":null,"open/robojev-4b-v2":0.03544887275269872,"open/robojev-4b-v3@0.25":0.4687906503677368,"open/robojev-4b-v3@0.5":0.2983299668082516,"open/robojev-4b-v3@0.75":0.2666072781234324,"open/robojev-4b-v3":0.1792055554427502,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.3855041020824851,"respan/span-02":0.28348783,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.27140203563694676,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0233154296875}},{"suite":"unseen","id":"rbm-ood/mit_franka/eddc195e-30c7-405f-aaf6-1ac3a4e4ff09","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"eddc195e-30c7-405f-aaf6-1ac3a4e4ff09","predictions":{"RoboJev-27B":0.05148425323287891,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.12383456021342108,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.09595038919331854,"Liquid D1":0.34864513533394575,"Mercury Decide":0.02297736752655447,"Cloudflare Clef":0.2768,"cloudflare/clef-flash":0.211,"cloudflare/clef-omni":0.1298,"liquid/d1-ultra":0.11671092037145396,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.014044934662909861,"open/robojev-27b":null,"open/robojev-4b-v2":0.0032876614041202805,"open/robojev-4b-v3@0.25":0.022977370768785477,"open/robojev-4b-v3@0.5":0.006692850574775813,"open/robojev-4b-v3@0.75":0.005604465074944334,"open/robojev-4b-v3":0.0053922199218183735,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.2838335348782322,"respan/span-02":0.10232702,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.14473292290509976,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.04736328125}},{"suite":"unseen","id":"rbm-ood/mit_franka/ede2ccec-63de-4297-9e03-c51508b83211","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"ede2ccec-63de-4297-9e03-c51508b83211","predictions":{"RoboJev-27B":0.50049147325158,"GPT-6 Astra":0.15,"GPT-6.1 Sol":0.15,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.5763613896128816,"TypeSafe Jev 1.14":0.36,"Perplexity Decider":0.6996529746971231,"Liquid D1":0.9850429162609263,"Mercury Decide":0.46879062662624377,"Cloudflare Clef":0.5593,"cloudflare/clef-flash":0.772,"cloudflare/clef-omni":0.2567,"liquid/d1-ultra":0.24316814877634804,"open/intern-decision-4b":0.4069889545588398,"open/robojev-27b-v1@0.5":0.35358095526769256,"open/robojev-27b":null,"open/robojev-4b-v2":0.04990557889898353,"open/robojev-4b-v3@0.25":0.9626730680465698,"open/robojev-4b-v3@0.5":0.9035094985644659,"open/robojev-4b-v3@0.75":0.8330143287656493,"open/robojev-4b-v3":0.6070151330675095,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.8362613457689764,"respan/span-02":0.7952811,"typesafe/jev-1.13":0.53,"JEV-27B-VL (10 frames)":0.6692650163383174,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.03955078125}},{"suite":"unseen","id":"rbm-ood/mit_franka/eea29928-bb0a-4e0a-9e92-7765a60f569b","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"eea29928-bb0a-4e0a-9e92-7765a60f569b","predictions":{"RoboJev-27B":0.961801670998298,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.96,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.9330138910411421,"TypeSafe Jev 1.14":0.91,"Perplexity Decider":0.9898064972434887,"Liquid D1":0.9973683264797899,"Mercury Decide":0.9989677688926596,"Cloudflare Clef":0.8387,"cloudflare/clef-flash":0.8256,"cloudflare/clef-omni":0.7835,"liquid/d1-ultra":0.9747409528224408,"open/intern-decision-4b":0.9290542163538821,"open/robojev-27b-v1@0.5":0.9929523928683442,"open/robojev-27b":null,"open/robojev-4b-v2":0.8618042684870219,"open/robojev-4b-v3@0.25":0.9902915358543396,"open/robojev-4b-v3@0.5":0.9871579519028945,"open/robojev-4b-v3@0.75":0.9710246026727085,"open/robojev-4b-v3":0.9380451002706788,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.975083784537782,"respan/span-02":0.90845877,"typesafe/jev-1.13":0.93,"JEV-27B-VL (10 frames)":0.9096143358266268,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.236328125}},{"suite":"unseen","id":"rbm-ood/mit_franka/eeb8b278-c25d-43bb-9df5-1813d46886cc","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"eeb8b278-c25d-43bb-9df5-1813d46886cc","predictions":{"RoboJev-27B":0.9650047649453055,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.912236144514893,"TypeSafe Jev 1.14":0.72,"Perplexity Decider":0.9838521733784047,"Liquid D1":0.985042909949026,"Mercury Decide":0.9796676465460353,"Cloudflare Clef":0.9124,"cloudflare/clef-flash":0.8136,"cloudflare/clef-omni":0.1068,"liquid/d1-ultra":0.9484617333569997,"open/intern-decision-4b":0.8678561574454184,"open/robojev-27b-v1@0.5":0.9811138988166008,"open/robojev-27b":null,"open/robojev-4b-v2":0.8330143331540432,"open/robojev-4b-v3@0.25":0.9840936064720154,"open/robojev-4b-v3@0.5":0.972148766331303,"open/robojev-4b-v3@0.75":0.8832743426844196,"open/robojev-4b-v3":0.6815425035280747,"openai/gpt-6-luna-decisions":0.76,"perplexity/pplx-decider-flash-v1.2":0.9437032652730335,"respan/span-02":0.9304895,"typesafe/jev-1.13":0.6,"JEV-27B-VL (10 frames)":0.9204514106263971,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006683349609375}},{"suite":"unseen","id":"rbm-ood/mit_franka/ef734a6a-b126-4701-ad2e-3bd7bcc3d892","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"ef734a6a-b126-4701-ad2e-3bd7bcc3d892","predictions":{"RoboJev-27B":0.674494114874223,"GPT-6 Astra":0.15,"GPT-6.1 Sol":0.18,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.7372774974811699,"TypeSafe Jev 1.14":0.71,"Perplexity Decider":0.8280799458455133,"Liquid D1":0.96267311613631,"Mercury Decide":0.8519528019683106,"Cloudflare Clef":0.5098,"cloudflare/clef-flash":0.551,"cloudflare/clef-omni":0.4676,"liquid/d1-ultra":0.549204909864935,"open/intern-decision-4b":0.7439389554145914,"open/robojev-27b-v1@0.5":0.9373043355009155,"open/robojev-27b":null,"open/robojev-4b-v2":0.005604465165684275,"open/robojev-4b-v3@0.25":0.9149009585380554,"open/robojev-4b-v3@0.5":0.25872010509521604,"open/robojev-4b-v3@0.75":0.15107550847556014,"open/robojev-4b-v3":0.10211768392406631,"openai/gpt-6-luna-decisions":0.39,"perplexity/pplx-decider-flash-v1.2":0.8061686343938219,"respan/span-02":0.79093933,"typesafe/jev-1.13":0.72,"JEV-27B-VL (10 frames)":0.7942829639440363,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.302734375}},{"suite":"unseen","id":"rbm-ood/mit_franka/ef82095d-6647-438b-ae41-33b46b745009","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"ef82095d-6647-438b-ae41-33b46b745009","predictions":{"RoboJev-27B":0.6361717803551603,"GPT-6 Astra":0.76,"GPT-6.1 Sol":0.76,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.16873732846057587,"TypeSafe Jev 1.14":0.21,"Perplexity Decider":0.22815734187755513,"Liquid D1":0.2689414213699951,"Mercury Decide":0.03732689136002139,"Cloudflare Clef":0.3263,"cloudflare/clef-flash":0.3499,"cloudflare/clef-omni":0.1457,"liquid/d1-ultra":0.3229012912817457,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.09366337103374121,"open/robojev-27b":null,"open/robojev-4b-v2":0.32865256165325696,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.1709446101989739,"open/robojev-4b-v3@0.75":0.1669856712343507,"open/robojev-4b-v3":0.08810813794451551,"openai/gpt-6-luna-decisions":0.11,"perplexity/pplx-decider-flash-v1.2":0.382426099953859,"respan/span-02":0.25301653,"typesafe/jev-1.13":0.36,"JEV-27B-VL (10 frames)":0.3171855170499604,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00970458984375}},{"suite":"unseen","id":"rbm-ood/mit_franka/f1a636c7-5760-4b3e-bdf4-9bd003f0172d","task":"Pour the pebbles from the cup onto the plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"f1a636c7-5760-4b3e-bdf4-9bd003f0172d","predictions":{"RoboJev-27B":0.856595812849096,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.8,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.691789911339813,"TypeSafe Jev 1.14":0.35,"Perplexity Decider":0.7753445281378282,"Liquid D1":0.7981867825403176,"Mercury Decide":0.9046505434556232,"Cloudflare Clef":0.7437,"cloudflare/clef-flash":0.6912,"cloudflare/clef-omni":0.4439,"liquid/d1-ultra":0.7993459209244324,"open/intern-decision-4b":0.3201997500236374,"open/robojev-27b-v1@0.5":0.9418781361045873,"open/robojev-27b":null,"open/robojev-4b-v2":0.008352675304716173,"open/robojev-4b-v3@0.25":0.970687747001648,"open/robojev-4b-v3@0.5":0.972148766331303,"open/robojev-4b-v3@0.75":0.9282107321543306,"open/robojev-4b-v3":0.8761560328980749,"openai/gpt-6-luna-decisions":0.76,"perplexity/pplx-decider-flash-v1.2":0.6743904569672409,"respan/span-02":0.26637816,"typesafe/jev-1.13":0.57,"JEV-27B-VL (10 frames)":0.6087596798173774,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.056640625}},{"suite":"unseen","id":"rbm-ood/mit_franka/f1aceb48-98fe-402a-ac86-6cf4989edc6f","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"f1aceb48-98fe-402a-ac86-6cf4989edc6f","predictions":{"RoboJev-27B":0.31973274960061976,"GPT-6 Astra":0.1,"GPT-6.1 Sol":0.06,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.442430526991256,"TypeSafe Jev 1.14":0.27,"Perplexity Decider":0.34888513494664003,"Liquid D1":0.9724147177732099,"Mercury Decide":0.18242551491653522,"Cloudflare Clef":0.5327,"cloudflare/clef-flash":0.8192,"cloudflare/clef-omni":0.3871,"liquid/d1-ultra":0.3229012912817457,"open/intern-decision-4b":0.778122175998967,"open/robojev-27b-v1@0.5":0.0550453249696564,"open/robojev-27b":null,"open/robojev-4b-v2":0.004293165515526464,"open/robojev-4b-v3@0.25":0.851952850818634,"open/robojev-4b-v3@0.5":0.21151967170194583,"open/robojev-4b-v3@0.75":0.09953688489563063,"open/robojev-4b-v3":0.06858087544025289,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.5495428831798008,"respan/span-02":0.8965051,"typesafe/jev-1.13":0.49,"JEV-27B-VL (10 frames)":0.46119127175395114,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.62109375}},{"suite":"unseen","id":"rbm-ood/mit_franka/f1e72daf-47b9-4017-9de1-8b760e30ba75","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"f1e72daf-47b9-4017-9de1-8b760e30ba75","predictions":{"RoboJev-27B":0.8470918728287281,"GPT-6 Astra":0.3,"GPT-6.1 Sol":0.85,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.7,"JEV-27B-VL":0.8710104893791976,"TypeSafe Jev 1.14":0.76,"Perplexity Decider":0.8842478952573724,"Liquid D1":0.8519527963298947,"Mercury Decide":0.9840936065096271,"Cloudflare Clef":0.3276,"cloudflare/clef-flash":0.3204,"cloudflare/clef-omni":0.5436,"liquid/d1-ultra":0.6551469107189953,"open/intern-decision-4b":0.3201997500236374,"open/robojev-27b-v1@0.5":0.9722060041773515,"open/robojev-27b":null,"open/robojev-4b-v2":0.003757049695787553,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.018939798044182644,"open/robojev-4b-v3@0.75":0.030697934885315165,"open/robojev-4b-v3":0.0721349360304201,"openai/gpt-6-luna-decisions":0.88,"perplexity/pplx-decider-flash-v1.2":0.5296739495644228,"respan/span-02":0.21232623,"typesafe/jev-1.13":0.77,"JEV-27B-VL (10 frames)":0.9049033028857881,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.12158203125}},{"suite":"unseen","id":"rbm-ood/mit_franka/f5171b6e-6bc8-47b6-8ffd-d8955acc9fea","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"f5171b6e-6bc8-47b6-8ffd-d8955acc9fea","predictions":{"RoboJev-27B":0.37378719127340615,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.35587583319537724,"TypeSafe Jev 1.14":0.34,"Perplexity Decider":0.3089666958847193,"Liquid D1":0.6224593312018546,"Mercury Decide":0.04742586796038571,"Cloudflare Clef":0.2742,"cloudflare/clef-flash":0.425,"cloudflare/clef-omni":0.2916,"liquid/d1-ultra":0.3674872816095884,"open/intern-decision-4b":0.42221451068097277,"open/robojev-27b-v1@0.5":0.05946833732274044,"open/robojev-27b":null,"open/robojev-4b-v2":0.003593602817215226,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.05241435048719427,"open/robojev-4b-v3@0.75":0.02580728323952834,"open/robojev-4b-v3":0.01421514020851167,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.5882360365278717,"respan/span-02":0.81729174,"typesafe/jev-1.13":0.21,"JEV-27B-VL (10 frames)":0.4979919432991276,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.236328125}},{"suite":"unseen","id":"rbm-ood/mit_franka/f5b509e0-b261-4452-83e4-62683008d0f4","task":"Pick up the banana from the blue plate and place it on the green plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"f5b509e0-b261-4452-83e4-62683008d0f4","predictions":{"RoboJev-27B":0.001031599261403426,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.000527665872182514,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.009810604558709125,"Liquid D1":0.039638836831964216,"Mercury Decide":0.0005884089215200299,"Cloudflare Clef":0.1282,"cloudflare/clef-flash":0.2079,"cloudflare/clef-omni":0.1305,"liquid/d1-ultra":0.05927725100508458,"open/intern-decision-4b":0.12511350509772579,"open/robojev-27b-v1@0.5":9.456067458686273e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.001842766452331557,"open/robojev-4b-v3@0.25":0.005220125894993544,"open/robojev-4b-v3@0.5":0.0019267347052741358,"open/robojev-4b-v3@0.75":0.0013488637996850762,"open/robojev-4b-v3":0.0009012109819517691,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.03576358145943186,"respan/span-02":0.74857783,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.003924902975873718,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0007781982421875}},{"suite":"unseen","id":"rbm-ood/mit_franka/f5e111a8-154d-4653-a5f6-3d8748f88fec","task":"Pour the pebbles from the cup onto the plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"f5e111a8-154d-4653-a5f6-3d8748f88fec","predictions":{"RoboJev-27B":0.08691566176839965,"GPT-6 Astra":0.25,"GPT-6.1 Sol":0.16,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.15515456412771056,"TypeSafe Jev 1.14":0.18,"Perplexity Decider":0.12146240526046737,"Liquid D1":0.6513548511303336,"Mercury Decide":0.029312228313453616,"Cloudflare Clef":0.1812,"cloudflare/clef-flash":0.5784,"cloudflare/clef-omni":0.3838,"liquid/d1-ultra":0.5613945046340345,"open/intern-decision-4b":0.5469149563843178,"open/robojev-27b-v1@0.5":0.11044521801265034,"open/robojev-27b":null,"open/robojev-4b-v2":0.07278720919427024,"open/robojev-4b-v3@0.25":0.9241418242454529,"open/robojev-4b-v3@0.5":0.9193991005705059,"open/robojev-4b-v3@0.75":0.4407557950301173,"open/robojev-4b-v3":0.2322495721973338,"openai/gpt-6-luna-decisions":0.65,"perplexity/pplx-decider-flash-v1.2":0.3205269183319847,"respan/span-02":0.7020785,"typesafe/jev-1.13":0.2,"JEV-27B-VL (10 frames)":0.12766073698618366,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00592041015625}},{"suite":"unseen","id":"rbm-ood/mit_franka/f921a32c-2344-4918-8329-3a13ff0d27bf","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"f921a32c-2344-4918-8329-3a13ff0d27bf","predictions":{"RoboJev-27B":0.30170717467071406,"GPT-6 Astra":0.06,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.2325290708138324,"TypeSafe Jev 1.14":0.33,"Perplexity Decider":0.19421187822835168,"Liquid D1":0.8354835371034369,"Mercury Decide":0.02595735606753309,"Cloudflare Clef":0.2017,"cloudflare/clef-flash":0.3743,"cloudflare/clef-omni":0.5737,"liquid/d1-ultra":0.23419873423953774,"open/intern-decision-4b":0.5930110454411601,"open/robojev-27b-v1@0.5":0.027426268660521346,"open/robojev-27b":null,"open/robojev-4b-v2":0.002631674205642126,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.018939798044182644,"open/robojev-4b-v3@0.75":0.010731211960485985,"open/robojev-4b-v3":0.007868747659394765,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.4274461957203657,"respan/span-02":0.15959975,"typesafe/jev-1.13":0.29,"JEV-27B-VL (10 frames)":0.2963850555734057,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.3984375}},{"suite":"unseen","id":"rbm-ood/mit_franka/f941604f-ad46-43ad-914a-2c53eef0bd8c","task":"Pull a tissue from the tissue box","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"f941604f-ad46-43ad-914a-2c53eef0bd8c","predictions":{"RoboJev-27B":0.9142875372487121,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.06552740959616077,"TypeSafe Jev 1.14":0.34,"Perplexity Decider":0.15680828717650297,"Liquid D1":0.5926666143433998,"Mercury Decide":0.02931223244728875,"Cloudflare Clef":0.4053,"cloudflare/clef-flash":0.2224,"cloudflare/clef-omni":0.48,"liquid/d1-ultra":0.2617952353661971,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.14392303695031675,"open/robojev-27b":null,"open/robojev-4b-v2":0.7772998717278379,"open/robojev-4b-v3@0.25":0.43782350420951843,"open/robojev-4b-v3@0.5":0.7152565465994749,"open/robojev-4b-v3@0.75":0.18420778945962635,"open/robojev-4b-v3":0.13612834674424493,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.36200986816593833,"respan/span-02":0.14128374,"typesafe/jev-1.13":0.32,"JEV-27B-VL (10 frames)":0.725088743823548,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.46875}},{"suite":"unseen","id":"rbm-ood/mit_franka/fa85c086-d384-4e53-a2d6-a7286b86e5c7","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"fa85c086-d384-4e53-a2d6-a7286b86e5c7","predictions":{"RoboJev-27B":0.4466793743876858,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.5076426485640868,"TypeSafe Jev 1.14":0.47,"Perplexity Decider":0.624161326252169,"Liquid D1":0.9626731169394882,"Mercury Decide":0.6224593312018546,"Cloudflare Clef":0.4489,"cloudflare/clef-flash":0.6708,"cloudflare/clef-omni":0.4315,"liquid/d1-ultra":0.2617952444643894,"open/intern-decision-4b":0.3201997500236374,"open/robojev-27b-v1@0.5":0.5687890350482805,"open/robojev-27b":null,"open/robojev-4b-v2":0.002751490629587489,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.0671334948723516,"open/robojev-4b-v3@0.75":0.05133579603952293,"open/robojev-4b-v3":0.028398519832920938,"openai/gpt-6-luna-decisions":0.19,"perplexity/pplx-decider-flash-v1.2":0.5985393119909318,"respan/span-02":0.6707347,"typesafe/jev-1.13":0.68,"JEV-27B-VL (10 frames)":0.5575251030211847,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.4921875}},{"suite":"unseen","id":"rbm-ood/mit_franka/faf4bcb1-d384-403c-829f-53b965fcd58d","task":"Fold the towel in half","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"faf4bcb1-d384-403c-829f-53b965fcd58d","predictions":{"RoboJev-27B":0.07358926180790719,"GPT-6 Astra":0.18,"GPT-6.1 Sol":0.14,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.13601654707145427,"TypeSafe Jev 1.14":0.24,"Perplexity Decider":0.07168906698913291,"Liquid D1":0.46879062662624377,"Mercury Decide":0.033085978746234736,"Cloudflare Clef":0.2671,"cloudflare/clef-flash":0.368,"cloudflare/clef-omni":0.2486,"liquid/d1-ultra":0.20868888924130843,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.010235588452912803,"open/robojev-27b":null,"open/robojev-4b-v2":0.27246679982051997,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.06312881727672377,"open/robojev-4b-v3@0.75":0.02167836395087896,"open/robojev-4b-v3":0.01499717745111633,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.2897424850382949,"respan/span-02":0.19146669,"typesafe/jev-1.13":0.32,"JEV-27B-VL (10 frames)":0.12249262620985958,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00628662109375}},{"suite":"unseen","id":"rbm-ood/mit_franka/fd33b95b-e031-4057-9356-453c63fa4f8d","task":"Pull a tissue from the tissue box","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"fd33b95b-e031-4057-9356-453c63fa4f8d","predictions":{"RoboJev-27B":0.9383301928767825,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.9146716309271947,"TypeSafe Jev 1.14":0.62,"Perplexity Decider":0.9335451195884692,"Liquid D1":0.9046505312448597,"Mercury Decide":0.9840936113496375,"Cloudflare Clef":0.9039,"cloudflare/clef-flash":0.7769,"cloudflare/clef-omni":0.8773,"liquid/d1-ultra":0.8930882603495018,"open/intern-decision-4b":0.788764540067536,"open/robojev-27b-v1@0.5":0.9917499092512754,"open/robojev-27b":null,"open/robojev-4b-v2":0.930168832912458,"open/robojev-4b-v3@0.25":0.9399133324623108,"open/robojev-4b-v3@0.5":0.8707824477141304,"open/robojev-4b-v3@0.75":0.35543389140488085,"open/robojev-4b-v3":0.2625786543234272,"openai/gpt-6-luna-decisions":0.92,"perplexity/pplx-decider-flash-v1.2":0.7947229326645716,"respan/span-02":0.81647724,"typesafe/jev-1.13":0.84,"JEV-27B-VL (10 frames)":0.9633687824662075,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.423828125}},{"suite":"unseen","id":"rbm-ood/mit_franka/ff20e79d-74a8-422d-86e6-48e3d81a5f7d","task":"Pick up the banana from the blue plate and place it on the green plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"mit_franka","episode":"ff20e79d-74a8-422d-86e6-48e3d81a5f7d","predictions":{"RoboJev-27B":0.29506281790838135,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.17310295992426264,"TypeSafe Jev 1.14":0.19,"Perplexity Decider":0.23480059782690144,"Liquid D1":0.6224593312018546,"Mercury Decide":0.06008665059478843,"Cloudflare Clef":0.2317,"cloudflare/clef-flash":0.6548,"cloudflare/clef-omni":0.629,"liquid/d1-ultra":0.22546161194543257,"open/intern-decision-4b":0.39193998888916504,"open/robojev-27b-v1@0.5":0.15450160137062205,"open/robojev-27b":null,"open/robojev-4b-v2":0.13296424849235422,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.10858632498619036,"open/robojev-4b-v3@0.75":0.06792255924998467,"open/robojev-4b-v3":0.047919347698515906,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3478994179133151,"respan/span-02":0.8877515,"typesafe/jev-1.13":0.51,"JEV-27B-VL (10 frames)":0.3352524829467311,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.640625}},{"suite":"unseen","id":"rbm-ood/usc_franka/115e12f1-8e7a-429c-bc7a-6e4086649d5d","task":"Put banana on plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"115e12f1-8e7a-429c-bc7a-6e4086649d5d","predictions":{"RoboJev-27B":0.9296508695715394,"GPT-6 Astra":0.84,"GPT-6.1 Sol":0.81,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.9344436772717867,"TypeSafe Jev 1.14":0.92,"Perplexity Decider":0.9353444354228135,"Liquid D1":0.9953904278719042,"Mercury Decide":0.9959298628956835,"Cloudflare Clef":0.9061,"cloudflare/clef-flash":0.9134,"cloudflare/clef-omni":0.3434,"liquid/d1-ultra":0.8727197255275911,"open/intern-decision-4b":0.778122175998967,"open/robojev-27b-v1@0.5":0.9699079333012062,"open/robojev-27b":null,"open/robojev-4b-v2":0.9069361009827602,"open/robojev-4b-v3@0.25":0.9820137619972229,"open/robojev-4b-v3@0.5":0.9592186718281821,"open/robojev-4b-v3@0.75":0.8892726892788834,"open/robojev-4b-v3":0.7955476296199337,"openai/gpt-6-luna-decisions":0.89,"perplexity/pplx-decider-flash-v1.2":0.9419347881366456,"respan/span-02":0.8191083,"typesafe/jev-1.13":0.93,"JEV-27B-VL (10 frames)":0.9269689170426918,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.92578125}},{"suite":"unseen","id":"rbm-ood/usc_franka/4804b50b-9efa-4844-8e4d-533bd403f71e","task":"Stack the red cube on the gray cube","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"4804b50b-9efa-4844-8e4d-533bd403f71e","predictions":{"RoboJev-27B":0.0018063461653938342,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.00010058276197295997,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.007826882548865117,"Liquid D1":0.0038244842833143086,"Mercury Decide":0.0008559008215187073,"Cloudflare Clef":0.0965,"cloudflare/clef-flash":0.1171,"cloudflare/clef-omni":0.1042,"liquid/d1-ultra":0.05927725297400196,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":4.654458975925398e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.0008635702282952242,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.004519892642389456,"open/robojev-4b-v3@0.75":0.003927901618504033,"open/robojev-4b-v3":0.0036922283157701354,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.06655941187609206,"respan/span-02":0.057887916,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":3.1628259637610934e-05,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.236328125}},{"suite":"unseen","id":"rbm-ood/usc_franka/4a7082b7-018e-49cd-8484-ab15695a71e9","task":"Put the yellow plate in the sink","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"4a7082b7-018e-49cd-8484-ab15695a71e9","predictions":{"RoboJev-27B":0.17394117013135296,"GPT-6 Astra":0.78,"GPT-6.1 Sol":0.78,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.5422027347558217,"TypeSafe Jev 1.14":0.71,"Perplexity Decider":0.7840206838662894,"Liquid D1":0.9830850845651248,"Mercury Decide":0.9399133536130195,"Cloudflare Clef":0.489,"cloudflare/clef-flash":0.714,"cloudflare/clef-omni":0.7449,"liquid/d1-ultra":0.867134682309721,"open/intern-decision-4b":0.7193152314525416,"open/robojev-27b-v1@0.5":0.9095394816472427,"open/robojev-27b":null,"open/robojev-4b-v2":0.2551315027042466,"open/robojev-4b-v3@0.25":0.9626730680465698,"open/robojev-4b-v3@0.5":0.9662767595980272,"open/robojev-4b-v3@0.75":0.9198621986336036,"open/robojev-4b-v3":0.8207944445572498,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.8403069729854328,"respan/span-02":0.86878633,"typesafe/jev-1.13":0.32,"JEV-27B-VL (10 frames)":0.37859340318739115,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.32421875}},{"suite":"unseen","id":"rbm-ood/usc_franka/5ff4a784-0bf9-42cc-9e69-66548ca8b1e8","task":"Put banana on plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"5ff4a784-0bf9-42cc-9e69-66548ca8b1e8","predictions":{"RoboJev-27B":0.9678939823423998,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.97980067479005,"TypeSafe Jev 1.14":0.94,"Perplexity Decider":0.9640602703716179,"Liquid D1":0.9990302478788304,"Mercury Decide":0.9995121429546471,"Cloudflare Clef":0.9549,"cloudflare/clef-flash":0.8142,"cloudflare/clef-omni":0.6263,"liquid/d1-ultra":0.9287049353094229,"open/intern-decision-4b":0.9290542163538821,"open/robojev-27b-v1@0.5":0.9847877889011565,"open/robojev-27b":null,"open/robojev-4b-v2":0.9823264950039196,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.9784541229757918,"open/robojev-4b-v3@0.75":0.93575028740662,"open/robojev-4b-v3":0.8573531996579977,"openai/gpt-6-luna-decisions":0.86,"perplexity/pplx-decider-flash-v1.2":0.9744884470609143,"respan/span-02":0.94404584,"typesafe/jev-1.13":0.95,"JEV-27B-VL (10 frames)":0.962356723736134,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.90234375}},{"suite":"unseen","id":"rbm-ood/usc_franka/94af8ff4-0f77-48fd-9a83-cc35fd060e66","task":"Put the yellow plate in the sink","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"94af8ff4-0f77-48fd-9a83-cc35fd060e66","predictions":{"RoboJev-27B":0.0032565373644044145,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.03857073479241521,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.10519469156479609,"Liquid D1":0.03514484690608697,"Mercury Decide":0.017986212133449052,"Cloudflare Clef":0.1074,"cloudflare/clef-flash":0.1224,"cloudflare/clef-omni":0.0932,"liquid/d1-ultra":0.12728026401359593,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.0003697661169848399,"open/robojev-27b":null,"open/robojev-4b-v2":0.033953688356658976,"open/robojev-4b-v3@0.25":0.03308597952127457,"open/robojev-4b-v3@0.5":0.013703364243695216,"open/robojev-4b-v3@0.75":0.007532610956861541,"open/robojev-4b-v3":0.003497602115726587,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.09256366220209372,"respan/span-02":0.16585656,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.0017334148569956287,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.057373046875}},{"suite":"unseen","id":"rbm-ood/usc_franka/a2dae243-c742-4d25-a09d-d18b6c0baebe","task":"Put banana on plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"a2dae243-c742-4d25-a09d-d18b6c0baebe","predictions":{"RoboJev-27B":0.0004424921385923884,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":1.3263264689226588e-06,"TypeSafe Jev 1.14":0.02,"Perplexity Decider":0.004397615265883111,"Liquid D1":0.024423088278887034,"Mercury Decide":0.00040448152043510435,"Cloudflare Clef":0.0293,"cloudflare/clef-flash":0.0859,"cloudflare/clef-omni":0.0335,"liquid/d1-ultra":0.024071707065305484,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":2.1687811090564452e-07,"open/robojev-27b":null,"open/robojev-4b-v2":0.001926734644431273,"open/robojev-4b-v3@0.25":0.014063626527786255,"open/robojev-4b-v3@0.5":0.004233320503182646,"open/robojev-4b-v3@0.75":0.0037017607703716303,"open/robojev-4b-v3":0.0025268270309959213,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.022749262899811242,"respan/span-02":0.040896934,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":1.4909159998706617e-06,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0179443359375}},{"suite":"unseen","id":"rbm-ood/usc_franka/a4ed8e1b-48f5-4125-9972-c07674af249e","task":"Stack the red cube on the gray cube","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"a4ed8e1b-48f5-4125-9972-c07674af249e","predictions":{"RoboJev-27B":0.0027757073908342336,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0049413478580747445,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.014226898979628868,"Liquid D1":0.00712142858769233,"Mercury Decide":0.0015011823572479975,"Cloudflare Clef":0.0832,"cloudflare/clef-flash":0.1137,"cloudflare/clef-omni":0.1042,"liquid/d1-ultra":0.026503363586022958,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.00044893925461170876,"open/robojev-27b":null,"open/robojev-4b-v2":0.001348863876427256,"open/robojev-4b-v3@0.25":0.014063626527786255,"open/robojev-4b-v3@0.5":0.0037133326112963453,"open/robojev-4b-v3@0.75":0.0032876613688676065,"open/robojev-4b-v3":0.0022671624120110317,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.15409081226162283,"respan/span-02":0.10454408,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.0014363199425326953,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.058349609375}},{"suite":"unseen","id":"rbm-ood/usc_franka/b9eb4443-1d51-4376-822a-aa3492642d04","task":"Stack the red cube on the gray cube","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"b9eb4443-1d51-4376-822a-aa3492642d04","predictions":{"RoboJev-27B":0.67063638485422,"GPT-6 Astra":0.87,"GPT-6.1 Sol":0.87,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.7646256022820459,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.567646640472918,"Liquid D1":0.26894141551050293,"Mercury Decide":0.18242551491653522,"Cloudflare Clef":0.3663,"cloudflare/clef-flash":0.4706,"cloudflare/clef-omni":0.2117,"liquid/d1-ultra":0.1272802561694866,"open/intern-decision-4b":0.5469149563843178,"open/robojev-27b-v1@0.5":0.898520550882293,"open/robojev-27b":null,"open/robojev-4b-v2":0.006124677327180011,"open/robojev-4b-v3@0.25":0.2689414322376251,"open/robojev-4b-v3@0.5":0.08561266237558948,"open/robojev-4b-v3@0.75":0.06424971259337996,"open/robojev-4b-v3":0.03505281632584716,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.443037452417074,"respan/span-02":0.3290956,"typesafe/jev-1.13":0.33,"JEV-27B-VL (10 frames)":0.8043663844226319,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.51171875}},{"suite":"unseen","id":"rbm-ood/usc_franka/c006a720-9007-4088-bd91-7b570c1bb238","task":"Put banana on plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"c006a720-9007-4088-bd91-7b570c1bb238","predictions":{"RoboJev-27B":0.0004475596083999086,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.01,"JEV-27B-VL":9.523870945295338e-07,"TypeSafe Jev 1.14":0.02,"Perplexity Decider":0.0046980288683680736,"Liquid D1":0.02297737225168171,"Mercury Decide":0.0002453695536504941,"Cloudflare Clef":0.0249,"cloudflare/clef-flash":0.0799,"cloudflare/clef-omni":0.0454,"liquid/d1-ultra":0.020827249508913296,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":4.7287231821397605e-07,"open/robojev-27b":null,"open/robojev-4b-v2":0.0020145213081092066,"open/robojev-4b-v3@0.25":0.01243165135383606,"open/robojev-4b-v3@0.5":0.0051522412018618095,"open/robojev-4b-v3@0.75":0.005282311488788821,"open/robojev-4b-v3":0.0053922199218183735,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.015741660361775444,"respan/span-02":0.039106738,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":2.0279534540864992e-06,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01068115234375}},{"suite":"unseen","id":"rbm-ood/usc_franka/c2a93b8e-5c54-4472-8ed9-d7abee1338fd","task":"Put the yellow plate in the sink","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"c2a93b8e-5c54-4472-8ed9-d7abee1338fd","predictions":{"RoboJev-27B":0.007076931545302494,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.029506098117647858,"TypeSafe Jev 1.14":0.02,"Perplexity Decider":0.15332439898413208,"Liquid D1":0.1561048974454574,"Mercury Decide":0.04208772431105632,"Cloudflare Clef":0.1646,"cloudflare/clef-flash":0.1104,"cloudflare/clef-omni":0.1047,"liquid/d1-ultra":0.19285321610173742,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.0030089520210720075,"open/robojev-27b":null,"open/robojev-4b-v2":0.00731334505501762,"open/robojev-4b-v3@0.25":0.022977370768785477,"open/robojev-4b-v3@0.5":0.008141294289513608,"open/robojev-4b-v3@0.75":0.005282311488788821,"open/robojev-4b-v3":0.0033132012876683184,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.08805849959639506,"respan/span-02":0.21845223,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.007965978559671032,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1484375}},{"suite":"unseen","id":"rbm-ood/usc_franka/d6b86600-6750-4e21-9892-b67442c97841","task":"Fold the towel in half","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"d6b86600-6750-4e21-9892-b67442c97841","predictions":{"RoboJev-27B":0.21252713820423594,"GPT-6 Astra":0.07,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.46917113044965597,"TypeSafe Jev 1.14":0.47,"Perplexity Decider":0.17967423678145217,"Liquid D1":0.966914024233187,"Mercury Decide":0.3486451217982255,"Cloudflare Clef":0.3028,"cloudflare/clef-flash":0.4589,"cloudflare/clef-omni":0.3291,"liquid/d1-ultra":0.41446124621639596,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.47659547113636114,"open/robojev-27b":null,"open/robojev-4b-v2":0.19332137351470816,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.04625107524610428,"open/robojev-4b-v3@0.75":0.019292242704938834,"open/robojev-4b-v3":0.010300413398065098,"openai/gpt-6-luna-decisions":0.1,"perplexity/pplx-decider-flash-v1.2":0.5888122444479722,"respan/span-02":0.41477105,"typesafe/jev-1.13":0.51,"JEV-27B-VL (10 frames)":0.2268468793400993,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.40625}},{"suite":"unseen","id":"rbm-ood/usc_franka/d8a0dba2-e4b3-4db3-bce7-60538500224d","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"d8a0dba2-e4b3-4db3-bce7-60538500224d","predictions":{"RoboJev-27B":0.529599322752104,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.2778170767516957,"TypeSafe Jev 1.14":0.27,"Perplexity Decider":0.11576635685077291,"Liquid D1":0.731058584489497,"Mercury Decide":0.10669059039516234,"Cloudflare Clef":0.1819,"cloudflare/clef-flash":0.3833,"cloudflare/clef-omni":0.4265,"liquid/d1-ultra":0.28131884207255187,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.2002275238567563,"open/robojev-27b":null,"open/robojev-4b-v2":0.966046311643341,"open/robojev-4b-v3@0.25":0.7057850360870361,"open/robojev-4b-v3@0.5":0.21151967170194583,"open/robojev-4b-v3@0.75":0.09953688489563063,"open/robojev-4b-v3":0.047919347698515906,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.4243253242607112,"respan/span-02":0.2784752,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.36296486975422865,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.65234375}},{"suite":"unseen","id":"rbm-ood/usc_franka/da0ecbfe-d086-4a01-857f-d0cdb9e30b72","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"da0ecbfe-d086-4a01-857f-d0cdb9e30b72","predictions":{"RoboJev-27B":0.6457401723121455,"GPT-6 Astra":0.91,"GPT-6.1 Sol":0.92,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.34014909255248615,"TypeSafe Jev 1.14":0.24,"Perplexity Decider":0.23620252566856878,"Liquid D1":0.754914975839675,"Mercury Decide":0.2689414213699951,"Cloudflare Clef":0.3482,"cloudflare/clef-flash":0.4889,"cloudflare/clef-omni":0.4766,"liquid/d1-ultra":0.3448530892810048,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.28144423904231014,"open/robojev-27b":null,"open/robojev-4b-v2":0.9241418190100563,"open/robojev-4b-v3@0.25":0.22270014882087708,"open/robojev-4b-v3@0.5":0.10858632498619036,"open/robojev-4b-v3@0.75":0.09432751595727837,"open/robojev-4b-v3":0.08810813794451551,"openai/gpt-6-luna-decisions":0.08,"perplexity/pplx-decider-flash-v1.2":0.34366948488066307,"respan/span-02":0.21320051,"typesafe/jev-1.13":0.24,"JEV-27B-VL (10 frames)":0.5500813763242776,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.72265625}},{"suite":"unseen","id":"rbm-ood/usc_franka/f86a35b5-ab99-4a53-baed-78f83995ef74","task":"Put the yellow plate in the sink","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"f86a35b5-ab99-4a53-baed-78f83995ef74","predictions":{"RoboJev-27B":0.6696431971672362,"GPT-6 Astra":0.87,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8710104893791976,"TypeSafe Jev 1.14":0.78,"Perplexity Decider":0.8155360452889763,"Liquid D1":0.989671846947603,"Mercury Decide":0.9324533060447605,"Cloudflare Clef":0.7395,"cloudflare/clef-flash":0.7207,"cloudflare/clef-omni":0.5108,"liquid/d1-ultra":0.8930882682158713,"open/intern-decision-4b":0.778122175998967,"open/robojev-27b-v1@0.5":0.897214231696881,"open/robojev-27b":null,"open/robojev-4b-v2":0.10927050321483402,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.972148766331303,"open/robojev-4b-v3@0.75":0.948664203960477,"open/robojev-4b-v3":0.9278650639695798,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.7226700089811054,"respan/span-02":0.7871608,"typesafe/jev-1.13":0.71,"JEV-27B-VL (10 frames)":0.8953936870369664,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.05419921875}},{"suite":"unseen","id":"rbm-ood/usc_franka/f8d7a3e1-c44f-42c8-836c-f650283551e9","task":"Stack the red cube on the gray cube","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"f8d7a3e1-c44f-42c8-836c-f650283551e9","predictions":{"RoboJev-27B":0.6029313094612361,"GPT-6 Astra":0.83,"GPT-6.1 Sol":0.78,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.7251689188957724,"TypeSafe Jev 1.14":0.22,"Perplexity Decider":0.5209811433519591,"Liquid D1":0.10087863219102594,"Mercury Decide":0.6791786926816161,"Cloudflare Clef":0.3499,"cloudflare/clef-flash":0.4953,"cloudflare/clef-omni":0.1503,"liquid/d1-ultra":0.26179524446438934,"open/intern-decision-4b":0.5469149563843178,"open/robojev-27b-v1@0.5":0.8825867402152038,"open/robojev-27b":null,"open/robojev-4b-v2":0.0022022489536237186,"open/robojev-4b-v3@0.25":0.7310585379600525,"open/robojev-4b-v3@0.5":0.1618215453479303,"open/robojev-4b-v3@0.75":0.09432751595727837,"open/robojev-4b-v3":0.047919347698515906,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.5974090394865955,"respan/span-02":0.4553036,"typesafe/jev-1.13":0.3,"JEV-27B-VL (10 frames)":0.7796883565855546,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.65625}},{"suite":"unseen","id":"rbm-ood/usc_franka/fd70a190-7043-4a8e-ac24-c3ea943856e5","task":"Fold the towel in half","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_franka","episode":"fd70a190-7043-4a8e-ac24-c3ea943856e5","predictions":{"RoboJev-27B":0.22062961252405372,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.2778170767516957,"TypeSafe Jev 1.14":0.48,"Perplexity Decider":0.12511840443080716,"Liquid D1":0.8807970779778823,"Mercury Decide":0.18242551936144574,"Cloudflare Clef":0.3307,"cloudflare/clef-flash":0.3581,"cloudflare/clef-omni":0.1842,"liquid/d1-ultra":0.3448530892810048,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.11039893497242195,"open/robojev-27b":null,"open/robojev-4b-v2":0.6614231852142245,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.059347834814291,"open/robojev-4b-v3@0.75":0.038631651048510164,"open/robojev-4b-v3":0.06195489972932116,"openai/gpt-6-luna-decisions":0.12,"perplexity/pplx-decider-flash-v1.2":0.5726798346960166,"respan/span-02":0.7676817,"typesafe/jev-1.13":0.59,"JEV-27B-VL (10 frames)":0.19641929261607063,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.462890625}},{"suite":"unseen","id":"rbm-ood/usc_koch/0687805b-46f9-40d0-b637-a58fe12db327","task":"Open the blue trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"0687805b-46f9-40d0-b637-a58fe12db327","predictions":{"RoboJev-27B":0.40792868482972067,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.08,"JEV-27B-VL":0.1855681031951678,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.14719717493328854,"Liquid D1":0.24508501864634827,"Mercury Decide":0.09534945718704857,"Cloudflare Clef":0.3401,"cloudflare/clef-flash":0.3499,"cloudflare/clef-omni":0.178,"liquid/d1-ultra":0.2617952535625818,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.05302828293233303,"open/robojev-27b":null,"open/robojev-4b-v2":0.01929224350793923,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.01664357488299338,"open/robojev-4b-v3@0.75":0.009538287541433899,"open/robojev-4b-v3":0.008304581719395627,"openai/gpt-6-luna-decisions":0.1,"perplexity/pplx-decider-flash-v1.2":0.25621231497421265,"respan/span-02":0.27781382,"typesafe/jev-1.13":0.27,"JEV-27B-VL (10 frames)":0.37642848091729725,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006500244140625}},{"suite":"unseen","id":"rbm-ood/usc_koch/06dd6133-b5d2-4a67-a489-082cf4b4a188","task":"Open the red trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"06dd6133-b5d2-4a67-a489-082cf4b4a188","predictions":{"RoboJev-27B":0.5387374214175669,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.028636536232379994,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.04401499803396567,"Liquid D1":0.08509904732734556,"Mercury Decide":0.004609572281931243,"Cloudflare Clef":0.258,"cloudflare/clef-flash":0.3056,"cloudflare/clef-omni":0.189,"liquid/d1-ultra":0.07129505806669395,"open/intern-decision-4b":0.1395062328236417,"open/robojev-27b-v1@0.5":0.0025959826269295176,"open/robojev-27b":null,"open/robojev-4b-v2":0.008730681628235537,"open/robojev-4b-v3@0.25":0.02595735713839531,"open/robojev-4b-v3@0.5":0.006269376036423619,"open/robojev-4b-v3@0.75":0.0041678002213721265,"open/robojev-4b-v3":0.0036922283157701354,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.05509111034282725,"respan/span-02":0.18929297,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.41717382165036654,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0047607421875}},{"suite":"unseen","id":"rbm-ood/usc_koch/099d39c2-c632-4b33-bdb4-2ab2b870b7b9","task":"Move the orange cup from left to right","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"099d39c2-c632-4b33-bdb4-2ab2b870b7b9","predictions":{"RoboJev-27B":0.9476890194698658,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.7808515707254183,"TypeSafe Jev 1.14":0.77,"Perplexity Decider":0.8948162147712133,"Liquid D1":0.9755769115435909,"Mercury Decide":0.8933094074745443,"Cloudflare Clef":0.6738,"cloudflare/clef-flash":0.7848,"cloudflare/clef-omni":0.1923,"liquid/d1-ultra":0.8220510037035875,"open/intern-decision-4b":0.767101934678807,"open/robojev-27b-v1@0.5":0.9528339422893888,"open/robojev-27b":null,"open/robojev-4b-v2":0.8066786264852919,"open/robojev-4b-v3@0.25":0.9626730680465698,"open/robojev-4b-v3@0.5":0.9703110587107732,"open/robojev-4b-v3@0.75":0.9635193115978655,"open/robojev-4b-v3":0.9684435763811455,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.8475846313386731,"respan/span-02":0.7323516,"typesafe/jev-1.13":0.75,"JEV-27B-VL (10 frames)":0.804188149998741,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.78515625}},{"suite":"unseen","id":"rbm-ood/usc_koch/0aed6592-49f7-48c0-96ad-dc7e9c7e7ad1","task":"Open the red trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"0aed6592-49f7-48c0-96ad-dc7e9c7e7ad1","predictions":{"RoboJev-27B":0.005458604203425477,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.002429537312945564,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.026315272924784815,"Liquid D1":0.0011695101780221189,"Mercury Decide":0.0013250222742561399,"Cloudflare Clef":0.2174,"cloudflare/clef-flash":0.2195,"cloudflare/clef-omni":0.1851,"liquid/d1-ultra":0.05400543319797551,"open/intern-decision-4b":0.11201237577359563,"open/robojev-27b-v1@0.5":0.00011588966459311921,"open/robojev-27b":null,"open/robojev-4b-v2":0.007990902069952163,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.0051522412018618095,"open/robojev-4b-v3@0.75":0.0041678002213721265,"open/robojev-4b-v3":0.004343237452522156,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.03134689372127317,"respan/span-02":0.047138646,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.017521645218924513,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0033721923828125}},{"suite":"unseen","id":"rbm-ood/usc_koch/0d368af7-daf1-411e-89d1-132d17ec73f5","task":"Move the orange cup from right to left","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"0d368af7-daf1-411e-89d1-132d17ec73f5","predictions":{"RoboJev-27B":0.6041451478349811,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.34014909255248615,"TypeSafe Jev 1.14":0.53,"Perplexity Decider":0.4067533517083507,"Liquid D1":0.9149009480320036,"Mercury Decide":0.047425872336085924,"Cloudflare Clef":0.6482,"cloudflare/clef-flash":0.2799,"cloudflare/clef-omni":0.4718,"liquid/d1-ultra":0.8426924838310659,"open/intern-decision-4b":0.5469149563843178,"open/robojev-27b-v1@0.5":0.24788383177276213,"open/robojev-27b":null,"open/robojev-4b-v2":0.06161735137356937,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.9640659266906685,"open/robojev-4b-v3@0.75":0.9770226303212622,"open/robojev-4b-v3":0.9667397146733209,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.20134262696311125,"respan/span-02":0.8266634,"typesafe/jev-1.13":0.31,"JEV-27B-VL (10 frames)":0.5647850642942848,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.66015625}},{"suite":"unseen","id":"rbm-ood/usc_koch/0e417347-7f7d-41ff-89d1-000a52ed164c","task":"Separate the purple and red cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"0e417347-7f7d-41ff-89d1-000a52ed164c","predictions":{"RoboJev-27B":0.06824578730215689,"GPT-6 Astra":0.05,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.08,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.03028791701097651,"TypeSafe Jev 1.14":0.17,"Perplexity Decider":0.1324180010170438,"Liquid D1":0.48438008427698437,"Mercury Decide":0.02297737016091733,"Cloudflare Clef":0.3695,"cloudflare/clef-flash":0.2333,"cloudflare/clef-omni":0.1094,"liquid/d1-ultra":0.17084219846972468,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.03911317154075133,"open/robojev-27b":null,"open/robojev-4b-v2":0.9500944211010165,"open/robojev-4b-v3@0.25":0.5,"open/robojev-4b-v3@0.5":0.34121268247291503,"open/robojev-4b-v3@0.75":0.3973146542214424,"open/robojev-4b-v3":0.2625786543234272,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.6798352025867042,"respan/span-02":0.3349008,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.05909481857174429,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000827789306640625}},{"suite":"unseen","id":"rbm-ood/usc_koch/0f6a53ad-2490-4687-a2d6-6478ad374733","task":"Open the red trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"0f6a53ad-2490-4687-a2d6-6478ad374733","predictions":{"RoboJev-27B":0.9602074472347689,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.9140685781231177,"TypeSafe Jev 1.14":0.81,"Perplexity Decider":0.8422232171572255,"Liquid D1":0.7057850402140659,"Mercury Decide":0.9933071506545437,"Cloudflare Clef":0.8943,"cloudflare/clef-flash":0.7659,"cloudflare/clef-omni":0.2368,"liquid/d1-ultra":0.9319051082383345,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.9932241411832372,"open/robojev-27b":null,"open/robojev-4b-v2":0.10927050321483402,"open/robojev-4b-v3@0.25":0.622459352016449,"open/robojev-4b-v3@0.5":0.7992444628236429,"open/robojev-4b-v3@0.75":0.9198621986336036,"open/robojev-4b-v3":0.9074264126806483,"openai/gpt-6-luna-decisions":0.93,"perplexity/pplx-decider-flash-v1.2":0.5378472264428272,"respan/span-02":0.0894877,"typesafe/jev-1.13":0.8,"JEV-27B-VL (10 frames)":0.9067461119442646,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.154296875}},{"suite":"unseen","id":"rbm-ood/usc_koch/1271eb80-7909-42e8-8a04-52c839be6a44","task":"Move the orange cup from right to left","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"1271eb80-7909-42e8-8a04-52c839be6a44","predictions":{"RoboJev-27B":0.934768310545684,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8881190238962514,"TypeSafe Jev 1.14":0.59,"Perplexity Decider":0.921843437902347,"Liquid D1":0.9783846677888324,"Mercury Decide":0.9740426434615237,"Cloudflare Clef":0.8669,"cloudflare/clef-flash":0.8545,"cloudflare/clef-omni":0.3313,"liquid/d1-ultra":0.829157791527048,"open/intern-decision-4b":0.6659927647326706,"open/robojev-27b-v1@0.5":0.9629198658451119,"open/robojev-27b":null,"open/robojev-4b-v2":0.06698650224956176,"open/robojev-4b-v3@0.25":0.9669140577316284,"open/robojev-4b-v3@0.5":0.972148766331303,"open/robojev-4b-v3@0.75":0.9635193115978655,"open/robojev-4b-v3":0.9314191245597471,"openai/gpt-6-luna-decisions":0.59,"perplexity/pplx-decider-flash-v1.2":0.9271718509010345,"respan/span-02":0.7703822,"typesafe/jev-1.13":0.78,"JEV-27B-VL (10 frames)":0.8226752413584943,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.263671875}},{"suite":"unseen","id":"rbm-ood/usc_koch/135694d3-39d1-4e45-9949-8fd75fc635c5","task":"Separate the purple and orange cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"135694d3-39d1-4e45-9949-8fd75fc635c5","predictions":{"RoboJev-27B":0.10703505135916197,"GPT-6 Astra":0.07,"GPT-6.1 Sol":0.07,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.13875488695089483,"TypeSafe Jev 1.14":0.2,"Perplexity Decider":0.19768477151203454,"Liquid D1":0.5621765008857981,"Mercury Decide":0.08509905312815914,"Cloudflare Clef":0.3253,"cloudflare/clef-flash":0.3911,"cloudflare/clef-omni":0.0783,"liquid/d1-ultra":0.25236785939789613,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.4798773941813321,"open/robojev-27b":null,"open/robojev-4b-v2":0.8618042684870219,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.23429597622173362,"open/robojev-4b-v3@0.75":0.18420778945962635,"open/robojev-4b-v3":0.3303678724294036,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.21145212054527798,"respan/span-02":0.21463676,"typesafe/jev-1.13":0.2,"JEV-27B-VL (10 frames)":0.07697202588645108,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00116729736328125}},{"suite":"unseen","id":"rbm-ood/usc_koch/1407d3b3-1d88-4df2-b8de-8cfbe0c5f314","task":"Open the green trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"1407d3b3-1d88-4df2-b8de-8cfbe0c5f314","predictions":{"RoboJev-27B":0.11261208729149191,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.3436150516418116,"TypeSafe Jev 1.14":0.14,"Perplexity Decider":0.07742962718484332,"Liquid D1":0.2689414213699951,"Mercury Decide":0.32082129433083023,"Cloudflare Clef":0.4923,"cloudflare/clef-flash":0.3595,"cloudflare/clef-omni":0.3048,"liquid/d1-ultra":0.39072106197134493,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.2860676657846126,"open/robojev-27b":null,"open/robojev-4b-v2":0.03863165331656982,"open/robojev-4b-v3@0.25":0.07585817575454712,"open/robojev-4b-v3@0.5":0.01664357488299338,"open/robojev-4b-v3@0.75":0.008992055872561407,"open/robojev-4b-v3":0.009760866998496955,"openai/gpt-6-luna-decisions":0.57,"perplexity/pplx-decider-flash-v1.2":0.29995678341730597,"respan/span-02":0.13636146,"typesafe/jev-1.13":0.29,"JEV-27B-VL (10 frames)":0.2668858803192125,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00860595703125}},{"suite":"unseen","id":"rbm-ood/usc_koch/1705cd6f-552d-4250-8e49-0f708c092b50","task":"Throw the orange cup away in the red trash can","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"1705cd6f-552d-4250-8e49-0f708c092b50","predictions":{"RoboJev-27B":0.8712258001451071,"GPT-6 Astra":0.8,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.830112995482166,"TypeSafe Jev 1.14":0.66,"Perplexity Decider":0.8618760262524894,"Liquid D1":0.9924227578357059,"Mercury Decide":0.9840936064221572,"Cloudflare Clef":0.8335,"cloudflare/clef-flash":0.7963,"cloudflare/clef-omni":0.3235,"liquid/d1-ultra":0.718681172204642,"open/intern-decision-4b":0.6932998143038492,"open/robojev-27b-v1@0.5":0.9708554565421579,"open/robojev-27b":null,"open/robojev-4b-v2":0.16698566684595678,"open/robojev-4b-v3@0.25":0.9046505093574524,"open/robojev-4b-v3@0.5":0.6438480526907612,"open/robojev-4b-v3@0.75":0.21256653766057104,"open/robojev-4b-v3":0.15646321933638418,"openai/gpt-6-luna-decisions":0.85,"perplexity/pplx-decider-flash-v1.2":0.398567368711088,"respan/span-02":0.87587434,"typesafe/jev-1.13":0.83,"JEV-27B-VL (10 frames)":0.8603008176395517,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.02978515625}},{"suite":"unseen","id":"rbm-ood/usc_koch/1821b533-7108-4abf-9faa-bd68a0698ee4","task":"Move the orange cup from right to left","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"1821b533-7108-4abf-9faa-bd68a0698ee4","predictions":{"RoboJev-27B":0.16804539079027972,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.22,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.17310295992426264,"TypeSafe Jev 1.14":0.36,"Perplexity Decider":0.26505276183733545,"Liquid D1":0.6791786861878392,"Mercury Decide":0.02033235542036712,"Cloudflare Clef":0.2463,"cloudflare/clef-flash":0.2333,"cloudflare/clef-omni":0.2259,"liquid/d1-ultra":0.5735104048478977,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.06238752617879148,"open/robojev-27b":null,"open/robojev-4b-v2":0.00731334505501762,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.1368024864039654,"open/robojev-4b-v3@0.75":0.1167256573155804,"open/robojev-4b-v3":0.08383818708105521,"openai/gpt-6-luna-decisions":0.56,"perplexity/pplx-decider-flash-v1.2":0.15023690079703117,"respan/span-02":0.16716582,"typesafe/jev-1.13":0.12,"JEV-27B-VL (10 frames)":0.2553160078626621,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1259765625}},{"suite":"unseen","id":"rbm-ood/usc_koch/1b1f62db-8d77-437e-875a-c2d622fe36bd","task":"Open the red trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"1b1f62db-8d77-437e-875a-c2d622fe36bd","predictions":{"RoboJev-27B":0.9416157387858455,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.9523904012103929,"TypeSafe Jev 1.14":0.89,"Perplexity Decider":0.9214277278338413,"Liquid D1":0.8175744761936437,"Mercury Decide":0.9975273774130499,"Cloudflare Clef":0.8955,"cloudflare/clef-flash":0.4853,"cloudflare/clef-omni":0.1814,"liquid/d1-ultra":0.9484617336446575,"open/intern-decision-4b":0.39193998888916504,"open/robojev-27b-v1@0.5":0.996719465522356,"open/robojev-27b":null,"open/robojev-4b-v2":0.031143833396690305,"open/robojev-4b-v3@0.25":0.9241418242454529,"open/robojev-4b-v3@0.5":0.9328665051276483,"open/robojev-4b-v3@0.75":0.9541617453379198,"open/robojev-4b-v3":0.952080652301484,"openai/gpt-6-luna-decisions":0.97,"perplexity/pplx-decider-flash-v1.2":0.6568943168175222,"respan/span-02":0.10259533,"typesafe/jev-1.13":0.79,"JEV-27B-VL (10 frames)":0.9341765620111825,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01544189453125}},{"suite":"unseen","id":"rbm-ood/usc_koch/1b743da9-8a11-4058-8dff-01f92e774ca9","task":"Open the blue trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"1b743da9-8a11-4058-8dff-01f92e774ca9","predictions":{"RoboJev-27B":0.6474048246891343,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.7142941616388551,"TypeSafe Jev 1.14":0.57,"Perplexity Decider":0.6002869877695247,"Liquid D1":0.5,"Mercury Decide":0.9324533102681759,"Cloudflare Clef":0.5212,"cloudflare/clef-flash":0.4357,"cloudflare/clef-omni":0.2484,"liquid/d1-ultra":0.7745383798334267,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.9016056598877499,"open/robojev-27b":null,"open/robojev-4b-v2":0.031143833396690305,"open/robojev-4b-v3@0.25":0.13296423852443695,"open/robojev-4b-v3@0.5":0.03164395527984847,"open/robojev-4b-v3@0.75":0.018197691623827453,"open/robojev-4b-v3":0.01582154176925847,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.2669811124196882,"respan/span-02":0.24246038,"typesafe/jev-1.13":0.48,"JEV-27B-VL (10 frames)":0.6363403391868746,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.02978515625}},{"suite":"unseen","id":"rbm-ood/usc_koch/1fa7f2e5-548a-410e-af82-1e2f11dbb0d5","task":"Move the orange cup from left to right","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"1fa7f2e5-548a-410e-af82-1e2f11dbb0d5","predictions":{"RoboJev-27B":0.8829292334820418,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.8497665318362629,"TypeSafe Jev 1.14":0.73,"Perplexity Decider":0.9137872926486279,"Liquid D1":0.939913350667554,"Mercury Decide":0.9579122686300086,"Cloudflare Clef":0.7728,"cloudflare/clef-flash":0.7948,"cloudflare/clef-omni":0.2267,"liquid/d1-ultra":0.872719733371701,"open/intern-decision-4b":0.42221451068097277,"open/robojev-27b-v1@0.5":0.9731896999039006,"open/robojev-27b":null,"open/robojev-4b-v2":0.5334321706777365,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.9286271325815819,"open/robojev-4b-v3@0.75":0.8949994162427413,"open/robojev-4b-v3":0.8573531996579977,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.8495564917034517,"respan/span-02":0.7251566,"typesafe/jev-1.13":0.8,"JEV-27B-VL (10 frames)":0.8059962496499078,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.81640625}},{"suite":"unseen","id":"rbm-ood/usc_koch/1fe53487-ca8b-403a-b429-36a8d1250447","task":"Separate the purple and red cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"1fe53487-ca8b-403a-b429-36a8d1250447","predictions":{"RoboJev-27B":0.7402351212166038,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.8344137624907007,"TypeSafe Jev 1.14":0.81,"Perplexity Decider":0.8805428148293768,"Liquid D1":0.946596671330088,"Mercury Decide":0.9770226298390826,"Cloudflare Clef":0.7223,"cloudflare/clef-flash":0.7908,"cloudflare/clef-omni":0.2261,"liquid/d1-ultra":0.5855387309336098,"open/intern-decision-4b":0.6229063460425425,"open/robojev-27b-v1@0.5":0.8486918555699123,"open/robojev-27b":null,"open/robojev-4b-v2":0.8135454576250908,"open/robojev-4b-v3@0.25":0.9626730680465698,"open/robojev-4b-v3@0.5":0.9662767595980272,"open/robojev-4b-v3@0.75":0.9425470270820971,"open/robojev-4b-v3":0.8927903235454209,"openai/gpt-6-luna-decisions":0.98,"perplexity/pplx-decider-flash-v1.2":0.8184850136008561,"respan/span-02":0.8557125,"typesafe/jev-1.13":0.85,"JEV-27B-VL (10 frames)":0.8035312846180084,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.08056640625}},{"suite":"unseen","id":"rbm-ood/usc_koch/24f819f4-0a30-4e20-9573-d17e5ef2fc11","task":"Move the orange cup from right to left","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"24f819f4-0a30-4e20-9573-d17e5ef2fc11","predictions":{"RoboJev-27B":0.19915665707709176,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.1890856950692309,"TypeSafe Jev 1.14":0.61,"Perplexity Decider":0.30893279494028597,"Liquid D1":0.46879062662624377,"Mercury Decide":0.9525741308615412,"Cloudflare Clef":0.1879,"cloudflare/clef-flash":0.276,"cloudflare/clef-omni":0.1594,"liquid/d1-ultra":0.5974659344706373,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.25571091141886587,"open/robojev-27b":null,"open/robojev-4b-v2":0.4776933853656969,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.25872010509521604,"open/robojev-4b-v3@0.75":0.36918510345682914,"open/robojev-4b-v3":0.472852806132433,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.8640378811902392,"respan/span-02":0.14427243,"typesafe/jev-1.13":0.29,"JEV-27B-VL (10 frames)":0.14392089881572528,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.11279296875}},{"suite":"unseen","id":"rbm-ood/usc_koch/29f4a914-5bec-4cf9-b8e0-05fd611fc207","task":"Open the red trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"29f4a914-5bec-4cf9-b8e0-05fd611fc207","predictions":{"RoboJev-27B":0.7603465234015465,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.7,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.7795307094673872,"TypeSafe Jev 1.14":0.58,"Perplexity Decider":0.6043581056090049,"Liquid D1":0.37754066879814546,"Mercury Decide":0.9046505338155469,"Cloudflare Clef":0.5525,"cloudflare/clef-flash":0.5517,"cloudflare/clef-omni":0.2143,"liquid/d1-ultra":0.7745383839439971,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.9701709100523445,"open/robojev-27b":null,"open/robojev-4b-v2":0.03251944279343901,"open/robojev-4b-v3@0.25":0.29421496391296387,"open/robojev-4b-v3@0.5":0.1368024864039654,"open/robojev-4b-v3@0.75":0.1107273107211166,"open/robojev-4b-v3":0.13612834674424493,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.298679114735843,"respan/span-02":0.09224394,"typesafe/jev-1.13":0.48,"JEV-27B-VL (10 frames)":0.6874156614605635,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.048095703125}},{"suite":"unseen","id":"rbm-ood/usc_koch/2ee340e3-bc00-4860-b6bf-b23b96fd0359","task":"Separate the purple and orange cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"2ee340e3-bc00-4860-b6bf-b23b96fd0359","predictions":{"RoboJev-27B":0.05678907281398397,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.016337251250490903,"TypeSafe Jev 1.14":0.14,"Perplexity Decider":0.06045494645020039,"Liquid D1":0.3629692055196168,"Mercury Decide":0.014063625674407,"Cloudflare Clef":0.2815,"cloudflare/clef-flash":0.2244,"cloudflare/clef-omni":0.0719,"liquid/d1-ultra":0.08552782226550981,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.05802028914468434,"open/robojev-27b":null,"open/robojev-4b-v2":0.7001924251222287,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.153095448827493,"open/robojev-4b-v3@0.75":0.14359896906129718,"open/robojev-4b-v3":0.1873394496953911,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2744985380381054,"respan/span-02":0.11315494,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.019515750226755713,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00093841552734375}},{"suite":"unseen","id":"rbm-ood/usc_koch/36925fed-6878-4520-beac-0490de9cc03c","task":"Throw the black marker away in the blue trash can","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"36925fed-6878-4520-beac-0490de9cc03c","predictions":{"RoboJev-27B":0.05770664858327895,"GPT-6 Astra":0.87,"GPT-6.1 Sol":0.84,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.38095940265371836,"TypeSafe Jev 1.14":0.33,"Perplexity Decider":0.20708401065555876,"Liquid D1":0.46879062662624377,"Mercury Decide":0.1329642384799526,"Cloudflare Clef":0.4305,"cloudflare/clef-flash":0.4211,"cloudflare/clef-omni":0.0823,"liquid/d1-ultra":0.46304399869958657,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.02340550505465895,"open/robojev-27b":null,"open/robojev-4b-v2":0.11369200859562456,"open/robojev-4b-v3@0.25":0.22270014882087708,"open/robojev-4b-v3@0.5":0.11512034374911738,"open/robojev-4b-v3@0.75":0.1107273107211166,"open/robojev-4b-v3":0.09257358731935178,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3318738025808174,"respan/span-02":0.15884523,"typesafe/jev-1.13":0.53,"JEV-27B-VL (10 frames)":0.16158763362305467,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00141143798828125}},{"suite":"unseen","id":"rbm-ood/usc_koch/37541aa9-a26c-4a0b-b415-7ce1851e45fc","task":"Move the orange cup from left to right","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"37541aa9-a26c-4a0b-b415-7ce1851e45fc","predictions":{"RoboJev-27B":0.7101903736522146,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.7576241042038823,"TypeSafe Jev 1.14":0.76,"Perplexity Decider":0.842567546409865,"Liquid D1":0.9796676475477876,"Mercury Decide":0.9399133443558416,"Cloudflare Clef":0.6582,"cloudflare/clef-flash":0.8602,"cloudflare/clef-omni":0.2133,"liquid/d1-ultra":0.8360373806888135,"open/intern-decision-4b":0.5930110454411601,"open/robojev-27b-v1@0.5":0.9058218897291325,"open/robojev-27b":null,"open/robojev-4b-v2":0.5223066146343031,"open/robojev-4b-v3@0.25":0.9465966820716858,"open/robojev-4b-v3@0.5":0.9328665051276483,"open/robojev-4b-v3@0.75":0.9056724840427216,"open/robojev-4b-v3":0.8761560328980749,"openai/gpt-6-luna-decisions":0.14,"perplexity/pplx-decider-flash-v1.2":0.9056777720212636,"respan/span-02":0.7388241,"typesafe/jev-1.13":0.81,"JEV-27B-VL (10 frames)":0.6760993123499905,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.3984375}},{"suite":"unseen","id":"rbm-ood/usc_koch/38c66aba-3e7f-4143-9d42-cafd96a81488","task":"Throw the black marker away in the blue trash can","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"38c66aba-3e7f-4143-9d42-cafd96a81488","predictions":{"RoboJev-27B":0.0024826717417463827,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.011046855431949719,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.01934223653580227,"Liquid D1":0.044680871544747154,"Mercury Decide":0.0033766116891041677,"Cloudflare Clef":0.106,"cloudflare/clef-flash":0.3154,"cloudflare/clef-omni":0.113,"liquid/d1-ultra":0.08174504553409896,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":8.824656552828754e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.0020145213081092066,"open/robojev-4b-v3@0.25":0.01798621006309986,"open/robojev-4b-v3@0.5":0.004233320503182646,"open/robojev-4b-v3@0.75":0.0025929030441612317,"open/robojev-4b-v3":0.002667578431318334,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.015189904754900872,"respan/span-02":0.14842916,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.008092162029335435,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000827789306640625}},{"suite":"unseen","id":"rbm-ood/usc_koch/3faeca25-e362-4701-933e-631858a0d3b7","task":"Throw the orange cup away in the red trash can","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"3faeca25-e362-4701-933e-631858a0d3b7","predictions":{"RoboJev-27B":0.9634849338282889,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.92,"JEV-27B-VL":0.9718813559367597,"TypeSafe Jev 1.14":0.73,"Perplexity Decider":0.9847616784907207,"Liquid D1":0.9830850852465428,"Mercury Decide":0.9992903294922534,"Cloudflare Clef":0.8353,"cloudflare/clef-flash":0.6538,"cloudflare/clef-omni":0.1194,"liquid/d1-ultra":0.9319051022634054,"open/intern-decision-4b":0.5313278281391198,"open/robojev-27b-v1@0.5":0.9936823709698475,"open/robojev-27b":null,"open/robojev-4b-v2":0.021996220940774924,"open/robojev-4b-v3@0.25":0.8933094143867493,"open/robojev-4b-v3@0.5":0.9475856495128058,"open/robojev-4b-v3@0.75":0.9566958954509301,"open/robojev-4b-v3":0.9649471836741528,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.2978796673438705,"respan/span-02":0.7431978,"typesafe/jev-1.13":0.23,"JEV-27B-VL (10 frames)":0.9695710221048365,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.12255859375}},{"suite":"unseen","id":"rbm-ood/usc_koch/40073104-3e83-46ad-9af1-0c3bcf2ca384","task":"Throw the black marker away in the blue trash can","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"40073104-3e83-46ad-9af1-0c3bcf2ca384","predictions":{"RoboJev-27B":0.3837475889599088,"GPT-6 Astra":0.74,"GPT-6.1 Sol":0.85,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.6061339568260653,"TypeSafe Jev 1.14":0.48,"Perplexity Decider":0.8644061648082197,"Liquid D1":0.9399133498259924,"Mercury Decide":0.5926665999540697,"Cloudflare Clef":0.529,"cloudflare/clef-flash":0.5648,"cloudflare/clef-omni":0.1246,"liquid/d1-ultra":0.6982966573119911,"open/intern-decision-4b":0.5,"open/robojev-27b-v1@0.5":0.5862728006378751,"open/robojev-27b":null,"open/robojev-4b-v2":0.6308148858171012,"open/robojev-4b-v3@0.25":0.622459352016449,"open/robojev-4b-v3@0.5":0.32658221149990796,"open/robojev-4b-v3@0.75":0.3419172570227415,"open/robojev-4b-v3":0.3800984297649739,"openai/gpt-6-luna-decisions":0.16,"perplexity/pplx-decider-flash-v1.2":0.3281903925640749,"respan/span-02":0.27853006,"typesafe/jev-1.13":0.77,"JEV-27B-VL (10 frames)":0.527895961953615,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006103515625}},{"suite":"unseen","id":"rbm-ood/usc_koch/4136d3de-2fa3-449a-a9c4-d9a9206ded09","task":"Move the orange cup from left to right","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"4136d3de-2fa3-449a-a9c4-d9a9206ded09","predictions":{"RoboJev-27B":0.9213699553566944,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.8108419090473843,"TypeSafe Jev 1.14":0.78,"Perplexity Decider":0.8847610745892464,"Liquid D1":0.952574130524949,"Mercury Decide":0.977022627413796,"Cloudflare Clef":0.661,"cloudflare/clef-flash":0.8049,"cloudflare/clef-omni":0.2951,"liquid/d1-ultra":0.9349716816032462,"open/intern-decision-4b":0.8089141677995819,"open/robojev-27b-v1@0.5":0.9694901327007321,"open/robojev-27b":null,"open/robojev-4b-v2":0.87699602202752,"open/robojev-4b-v3@0.25":0.977022647857666,"open/robojev-4b-v3@0.5":0.9770226296926641,"open/robojev-4b-v3@0.75":0.9566958954509301,"open/robojev-4b-v3":0.944069345153315,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.9482784851014867,"respan/span-02":0.62880313,"typesafe/jev-1.13":0.83,"JEV-27B-VL (10 frames)":0.8911766974668276,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.80859375}},{"suite":"unseen","id":"rbm-ood/usc_koch/414634c3-c744-42f6-a9b3-249aef0316fa","task":"Throw the black marker away in the blue trash can","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"414634c3-c744-42f6-a9b3-249aef0316fa","predictions":{"RoboJev-27B":0.1537755608688256,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.23528944636627316,"TypeSafe Jev 1.14":0.57,"Perplexity Decider":0.4599046414094446,"Liquid D1":0.9241418199787566,"Mercury Decide":0.09534947453918644,"Cloudflare Clef":0.5266,"cloudflare/clef-flash":0.5254,"cloudflare/clef-omni":0.113,"liquid/d1-ultra":0.5369560013004135,"open/intern-decision-4b":0.5777854893190272,"open/robojev-27b-v1@0.5":0.029485994899649533,"open/robojev-27b":null,"open/robojev-4b-v2":0.03251944279343901,"open/robojev-4b-v3@0.25":0.6513549089431763,"open/robojev-4b-v3@0.5":0.12199371684192196,"open/robojev-4b-v3@0.75":0.08463674788192488,"open/robojev-4b-v3":0.09724120311457327,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.42492040637594797,"respan/span-02":0.26712242,"typesafe/jev-1.13":0.49,"JEV-27B-VL (10 frames)":0.1610136663325809,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.046630859375}},{"suite":"unseen","id":"rbm-ood/usc_koch/45d64f1b-a29c-4319-9589-aeb65ed8a153","task":"Separate the purple and red cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"45d64f1b-a29c-4319-9589-aeb65ed8a153","predictions":{"RoboJev-27B":0.9030570847494774,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":0.848780582968663,"TypeSafe Jev 1.14":0.86,"Perplexity Decider":0.8779435095972646,"Liquid D1":0.9914225148714039,"Mercury Decide":0.9859363697283613,"Cloudflare Clef":0.8722,"cloudflare/clef-flash":0.7635,"cloudflare/clef-omni":0.2761,"liquid/d1-ultra":0.8553419749072408,"open/intern-decision-4b":0.8678561574454184,"open/robojev-27b-v1@0.5":0.9222340706899284,"open/robojev-27b":null,"open/robojev-4b-v2":0.9579122700410143,"open/robojev-4b-v3@0.25":0.9626730680465698,"open/robojev-4b-v3@0.5":0.940652165185709,"open/robojev-4b-v3@0.75":0.8769960242027004,"open/robojev-4b-v3":0.7955476296199337,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.8677327922448923,"respan/span-02":0.86193997,"typesafe/jev-1.13":0.89,"JEV-27B-VL (10 frames)":0.9042356193194836,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.275390625}},{"suite":"unseen","id":"rbm-ood/usc_koch/45d8c456-0ae2-4a23-9d5a-f9a946806d5b","task":"Throw the orange cup away in the red trash can","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"45d8c456-0ae2-4a23-9d5a-f9a946806d5b","predictions":{"RoboJev-27B":0.007080920429330259,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.004312659616623273,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.02508957837252043,"Liquid D1":0.0850990357257195,"Mercury Decide":0.0011695101083954067,"Cloudflare Clef":0.0827,"cloudflare/clef-flash":0.1978,"cloudflare/clef-omni":0.1563,"liquid/d1-ultra":0.16396262576456408,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.003387092629768289,"open/robojev-27b":null,"open/robojev-4b-v2":0.006996270681650968,"open/robojev-4b-v3@0.25":0.020332353189587593,"open/robojev-4b-v3@0.5":0.011276606158891207,"open/robojev-4b-v3@0.75":0.007100415903386552,"open/robojev-4b-v3":0.006341061537493235,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.048508568639201465,"respan/span-02":0.07344589,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.01683219793255462,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00096893310546875}},{"suite":"unseen","id":"rbm-ood/usc_koch/46a72685-0ed3-43d9-9154-88d8c4d90c7d","task":"Move the orange cup from right to left","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"46a72685-0ed3-43d9-9154-88d8c4d90c7d","predictions":{"RoboJev-27B":0.9101187227577742,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8290240080788286,"TypeSafe Jev 1.14":0.71,"Perplexity Decider":0.813977582595155,"Liquid D1":0.9850429156571794,"Mercury Decide":0.9525741283370988,"Cloudflare Clef":0.8373,"cloudflare/clef-flash":0.8444,"cloudflare/clef-omni":0.3619,"liquid/d1-ultra":0.8426924853912474,"open/intern-decision-4b":0.6518947636686268,"open/robojev-27b-v1@0.5":0.9364941430564138,"open/robojev-27b":null,"open/robojev-4b-v2":0.14917689162532846,"open/robojev-4b-v3@0.25":0.977022647857666,"open/robojev-4b-v3@0.5":0.9833564251170067,"open/robojev-4b-v3@0.75":0.9655548037210256,"open/robojev-4b-v3":0.9348103782119872,"openai/gpt-6-luna-decisions":0.16,"perplexity/pplx-decider-flash-v1.2":0.9235995174775262,"respan/span-02":0.6500456,"typesafe/jev-1.13":0.78,"JEV-27B-VL (10 frames)":0.839465608235022,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.46875}},{"suite":"unseen","id":"rbm-ood/usc_koch/46cd47bb-f690-4937-96a3-124567a31bb3","task":"Separate the purple and red cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"46cd47bb-f690-4937-96a3-124567a31bb3","predictions":{"RoboJev-27B":0.9386103663754958,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.9,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.8692698721717443,"TypeSafe Jev 1.14":0.71,"Perplexity Decider":0.8918150019940979,"Liquid D1":0.9914225154733152,"Mercury Decide":0.985936372311076,"Cloudflare Clef":0.8617,"cloudflare/clef-flash":0.8395,"cloudflare/clef-omni":0.3733,"liquid/d1-ultra":0.8071467838982626,"open/intern-decision-4b":0.8940776460411956,"open/robojev-27b-v1@0.5":0.9354167763712727,"open/robojev-27b":null,"open/robojev-4b-v2":0.930168832912458,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.9822447263824892,"open/robojev-4b-v3@0.75":0.9710246026727085,"open/robojev-4b-v3":0.9380451002706788,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.9081012528275438,"respan/span-02":0.89418715,"typesafe/jev-1.13":0.9,"JEV-27B-VL (10 frames)":0.894600945913063,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.208984375}},{"suite":"unseen","id":"rbm-ood/usc_koch/4737d874-045b-4596-aa0d-8841baca7581","task":"Separate the red and orange cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"4737d874-045b-4596-aa0d-8841baca7581","predictions":{"RoboJev-27B":0.9363608462706327,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.8497665318362629,"TypeSafe Jev 1.14":0.64,"Perplexity Decider":0.9052167561256186,"Liquid D1":0.9796676442828175,"Mercury Decide":0.9875683494440967,"Cloudflare Clef":0.8331,"cloudflare/clef-flash":0.8415,"cloudflare/clef-omni":0.2504,"liquid/d1-ultra":0.8071467765700858,"open/intern-decision-4b":0.8363317223730603,"open/robojev-27b-v1@0.5":0.9141606146332067,"open/robojev-27b":null,"open/robojev-4b-v2":0.8202227117180728,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.8707824477141304,"open/robojev-4b-v3@0.75":0.787433462339429,"open/robojev-4b-v3":0.3800984297649739,"openai/gpt-6-luna-decisions":0.92,"perplexity/pplx-decider-flash-v1.2":0.8644305306532599,"respan/span-02":0.3313026,"typesafe/jev-1.13":0.86,"JEV-27B-VL (10 frames)":0.8878562498762168,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.051025390625}},{"suite":"unseen","id":"rbm-ood/usc_koch/474ce398-376a-4781-a953-c15b4cc9c865","task":"Open the blue trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"474ce398-376a-4781-a953-c15b4cc9c865","predictions":{"RoboJev-27B":0.022149012726004277,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.09213794677531731,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.1382967448549779,"Liquid D1":0.05033063402195221,"Mercury Decide":0.06754669067036073,"Cloudflare Clef":0.1062,"cloudflare/clef-flash":0.079,"cloudflare/clef-omni":0.0535,"liquid/d1-ultra":0.07463356970542014,"open/intern-decision-4b":0.11201237577359563,"open/robojev-27b-v1@0.5":0.008579695534029794,"open/robojev-27b":null,"open/robojev-4b-v2":0.13296424849235422,"open/robojev-4b-v3@0.25":0.02595735713839531,"open/robojev-4b-v3@0.5":0.010566189227213266,"open/robojev-4b-v3@0.75":0.006308531582070822,"open/robojev-4b-v3":0.004343237452522156,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.12966839078919495,"respan/span-02":0.1294053,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.04753372098067864,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00113677978515625}},{"suite":"unseen","id":"rbm-ood/usc_koch/4d324a24-2ef1-4db0-b336-cca23179abee","task":"Separate the purple and orange cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"4d324a24-2ef1-4db0-b336-cca23179abee","predictions":{"RoboJev-27B":0.9125641894700793,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.8143605393978726,"TypeSafe Jev 1.14":0.8,"Perplexity Decider":0.9061943928689785,"Liquid D1":0.9902915227663948,"Mercury Decide":0.9770226310099107,"Cloudflare Clef":0.8606,"cloudflare/clef-flash":0.8198,"cloudflare/clef-omni":0.1553,"liquid/d1-ultra":0.7476321406021039,"open/intern-decision-4b":0.8527907640733415,"open/robojev-27b-v1@0.5":0.9646481931310101,"open/robojev-27b":null,"open/robojev-4b-v2":0.7185943895092446,"open/robojev-4b-v3@0.25":0.9465966820716858,"open/robojev-4b-v3@0.5":0.9368711827232762,"open/robojev-4b-v3@0.75":0.9056724840427216,"open/robojev-4b-v3":0.863871653255755,"openai/gpt-6-luna-decisions":0.9,"perplexity/pplx-decider-flash-v1.2":0.8914001613644154,"respan/span-02":0.82654124,"typesafe/jev-1.13":0.83,"JEV-27B-VL (10 frames)":0.8854607464749485,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.11572265625}},{"suite":"unseen","id":"rbm-ood/usc_koch/504099e1-3595-4b81-b8ff-99bfc6e68b88","task":"Separate the purple and red cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"504099e1-3595-4b81-b8ff-99bfc6e68b88","predictions":{"RoboJev-27B":0.8822081706735256,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.62,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.5987552114940351,"TypeSafe Jev 1.14":0.66,"Perplexity Decider":0.8198515063797769,"Liquid D1":0.9875683514793386,"Mercury Decide":0.9525741258126562,"Cloudflare Clef":0.7316,"cloudflare/clef-flash":0.847,"cloudflare/clef-omni":0.5722,"liquid/d1-ultra":0.7658012573170664,"open/intern-decision-4b":0.8363317223730603,"open/robojev-27b-v1@0.5":0.9155881391378171,"open/robojev-27b":null,"open/robojev-4b-v2":0.9272127908057297,"open/robojev-4b-v3@0.25":0.970687747001648,"open/robojev-4b-v3@0.5":0.9537489247538957,"open/robojev-4b-v3@0.75":0.915363252118075,"open/robojev-4b-v3":0.8927903235454209,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.8913158432753713,"respan/span-02":0.8319499,"typesafe/jev-1.13":0.7,"JEV-27B-VL (10 frames)":0.7485158751707668,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.02001953125}},{"suite":"unseen","id":"rbm-ood/usc_koch/5a357cb6-7e5b-4dae-971f-c8a037611468","task":"Open the green trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"5a357cb6-7e5b-4dae-971f-c8a037611468","predictions":{"RoboJev-27B":0.07126180264979287,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.3097538282682883,"TypeSafe Jev 1.14":0.3,"Perplexity Decider":0.07272151675618657,"Liquid D1":0.34864513533394575,"Mercury Decide":0.18242552380635632,"Cloudflare Clef":0.437,"cloudflare/clef-flash":0.3305,"cloudflare/clef-omni":0.1779,"liquid/d1-ultra":0.2813188325544226,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.20442087271127188,"open/robojev-27b":null,"open/robojev-4b-v2":0.027346786441616523,"open/robojev-4b-v3@0.25":0.022977370768785477,"open/robojev-4b-v3@0.5":0.005872534859081002,"open/robojev-4b-v3@0.75":0.0037017607703716303,"open/robojev-4b-v3":0.003138491707937668,"openai/gpt-6-luna-decisions":0.18,"perplexity/pplx-decider-flash-v1.2":0.21415535490608756,"respan/span-02":0.20649779,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.14600498616203245,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00102996826171875}},{"suite":"unseen","id":"rbm-ood/usc_koch/5cfc02b2-5402-44d7-9314-d490dfb48f10","task":"Throw the black marker away in the blue trash can","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"5cfc02b2-5402-44d7-9314-d490dfb48f10","predictions":{"RoboJev-27B":0.8383363704041529,"GPT-6 Astra":0.84,"GPT-6.1 Sol":0.2,"Claude Opus 5.5":0.65,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.8948238627857265,"TypeSafe Jev 1.14":0.72,"Perplexity Decider":0.9649753524273533,"Liquid D1":0.9706877671287282,"Mercury Decide":0.9953904277095224,"Cloudflare Clef":0.6374,"cloudflare/clef-flash":0.5632,"cloudflare/clef-omni":0.0846,"liquid/d1-ultra":0.7382047646338029,"open/intern-decision-4b":0.8527907640733415,"open/robojev-27b-v1@0.5":0.9734596925447347,"open/robojev-27b":null,"open/robojev-4b-v2":0.2998075748777713,"open/robojev-4b-v3@0.25":0.957912266254425,"open/robojev-4b-v3@0.5":0.8780062831580779,"open/robojev-4b-v3@0.75":0.7448684965407143,"open/robojev-4b-v3":0.632621183102026,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.5041176341903782,"respan/span-02":0.7504324,"typesafe/jev-1.13":0.79,"JEV-27B-VL (10 frames)":0.915365583475838,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00170135498046875}},{"suite":"unseen","id":"rbm-ood/usc_koch/5d703190-0df1-4daa-9088-0a45852f696c","task":"Open the red trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"5d703190-0df1-4daa-9088-0a45852f696c","predictions":{"RoboJev-27B":0.9543833889397936,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":0.9259516159535739,"TypeSafe Jev 1.14":0.75,"Perplexity Decider":0.8391898681195125,"Liquid D1":0.34864513533394575,"Mercury Decide":0.9971990726231805,"Cloudflare Clef":0.7229,"cloudflare/clef-flash":0.4743,"cloudflare/clef-omni":0.3734,"liquid/d1-ultra":0.910531392135771,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.9909622702861124,"open/robojev-27b":null,"open/robojev-4b-v2":0.7362922553128872,"open/robojev-4b-v3@0.25":0.957912266254425,"open/robojev-4b-v3@0.5":0.9810602019558173,"open/robojev-4b-v3@0.75":0.9807077572950611,"open/robojev-4b-v3":0.9782115888298761,"openai/gpt-6-luna-decisions":0.97,"perplexity/pplx-decider-flash-v1.2":0.6829001193170994,"respan/span-02":0.70237875,"typesafe/jev-1.13":0.66,"JEV-27B-VL (10 frames)":0.9162942684165135,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.06005859375}},{"suite":"unseen","id":"rbm-ood/usc_koch/5ed9b84b-e9f9-4557-ae59-e805128720f6","task":"Move the orange cup from left to right","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"5ed9b84b-e9f9-4557-ae59-e805128720f6","predictions":{"RoboJev-27B":0.009127976052794345,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0005922523292504315,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.013625013151389254,"Liquid D1":0.013222824085465766,"Mercury Decide":0.0005193049341029747,"Cloudflare Clef":0.1019,"cloudflare/clef-flash":0.1179,"cloudflare/clef-omni":0.1904,"liquid/d1-ultra":0.04692037976224143,"open/intern-decision-4b":0.11840617139815589,"open/robojev-27b-v1@0.5":0.0002230053351932551,"open/robojev-27b":null,"open/robojev-4b-v2":0.0034372413231743533,"open/robojev-4b-v3@0.25":0.008577484637498856,"open/robojev-4b-v3@0.5":0.007144725422878838,"open/robojev-4b-v3@0.75":0.01011736424150334,"open/robojev-4b-v3":0.018571313779720225,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.02217043385463321,"respan/span-02":0.11714814,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.0012459208972733014,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00070953369140625}},{"suite":"unseen","id":"rbm-ood/usc_koch/61ce528d-4829-4878-9647-0498d3e2b6b9","task":"Throw the black marker away in the blue trash can","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"61ce528d-4829-4878-9647-0498d3e2b6b9","predictions":{"RoboJev-27B":0.8252937767421117,"GPT-6 Astra":0.84,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.6835185788186595,"TypeSafe Jev 1.14":0.68,"Perplexity Decider":0.7070565729089555,"Liquid D1":0.8933094032139576,"Mercury Decide":0.9046505453836383,"Cloudflare Clef":0.6359,"cloudflare/clef-flash":0.4585,"cloudflare/clef-omni":0.0838,"liquid/d1-ultra":0.8832890747753159,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.8412089427260615,"open/robojev-27b":null,"open/robojev-4b-v2":0.002631674205642126,"open/robojev-4b-v3@0.25":0.22270014882087708,"open/robojev-4b-v3@0.5":0.386860966015097,"open/robojev-4b-v3@0.75":0.8564010309387029,"open/robojev-4b-v3":0.8573531996579977,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3286796610469769,"respan/span-02":0.088820755,"typesafe/jev-1.13":0.83,"JEV-27B-VL (10 frames)":0.7375915414054975,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.046630859375}},{"suite":"unseen","id":"rbm-ood/usc_koch/65aa1d59-fd81-4609-9b05-1f09bd66bb47","task":"Throw the orange cup away in the red trash can","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"65aa1d59-fd81-4609-9b05-1f09bd66bb47","predictions":{"RoboJev-27B":0.05331704156910775,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.027378666728553335,"TypeSafe Jev 1.14":0.11,"Perplexity Decider":0.04706157868083349,"Liquid D1":0.9241418210233833,"Mercury Decide":0.005220126786549345,"Cloudflare Clef":0.2862,"cloudflare/clef-flash":0.6457,"cloudflare/clef-omni":0.2028,"liquid/d1-ultra":0.10228896652269512,"open/intern-decision-4b":0.6932998143038492,"open/robojev-27b-v1@0.5":0.014664814192484082,"open/robojev-27b":null,"open/robojev-4b-v2":0.011895327908303815,"open/robojev-4b-v3@0.25":0.5926666259765625,"open/robojev-4b-v3@0.5":0.21151967170194583,"open/robojev-4b-v3@0.75":0.13643297762397494,"open/robojev-4b-v3":0.11806640532074496,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.18085566943666656,"respan/span-02":0.032850407,"typesafe/jev-1.13":0.36,"JEV-27B-VL (10 frames)":0.04519030149481951,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00555419921875}},{"suite":"unseen","id":"rbm-ood/usc_koch/661419ab-d66a-4025-8b88-ed6891cc58a9","task":"Open the green trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"661419ab-d66a-4025-8b88-ed6891cc58a9","predictions":{"RoboJev-27B":0.9576799788580073,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.7632365620986434,"TypeSafe Jev 1.14":0.63,"Perplexity Decider":0.6611082217418645,"Liquid D1":0.7981867777396212,"Mercury Decide":0.9241418152779357,"Cloudflare Clef":0.7656,"cloudflare/clef-flash":0.6235,"cloudflare/clef-omni":0.2241,"liquid/d1-ultra":0.9484617337884865,"open/intern-decision-4b":0.6659927647326706,"open/robojev-27b-v1@0.5":0.9560695476788598,"open/robojev-27b":null,"open/robojev-4b-v2":0.6811210474999878,"open/robojev-4b-v3@0.25":0.9669140577316284,"open/robojev-4b-v3@0.5":0.9662767595980272,"open/robojev-4b-v3@0.75":0.9613683489514899,"open/robojev-4b-v3":0.9495393243071166,"openai/gpt-6-luna-decisions":0.87,"perplexity/pplx-decider-flash-v1.2":0.9284058213176349,"respan/span-02":0.94523907,"typesafe/jev-1.13":0.52,"JEV-27B-VL (10 frames)":0.8433263078224973,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.007110595703125}},{"suite":"unseen","id":"rbm-ood/usc_koch/6789878d-b12a-4666-a897-329f07d794c8","task":"Separate the red and orange cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"6789878d-b12a-4666-a897-329f07d794c8","predictions":{"RoboJev-27B":0.9163924561072435,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.9032105469251083,"TypeSafe Jev 1.14":0.77,"Perplexity Decider":0.9406269011199946,"Liquid D1":0.9688561672170913,"Mercury Decide":0.992422757072337,"Cloudflare Clef":0.8968,"cloudflare/clef-flash":0.7942,"cloudflare/clef-omni":0.1734,"liquid/d1-ultra":0.7745383798334267,"open/intern-decision-4b":0.8879876242264044,"open/robojev-27b-v1@0.5":0.9855289105045523,"open/robojev-27b":null,"open/robojev-4b-v2":0.930168832912458,"open/robojev-4b-v3@0.25":0.9669140577316284,"open/robojev-4b-v3@0.5":0.9442201868171092,"open/robojev-4b-v3@0.75":0.6580827429772586,"open/robojev-4b-v3":0.2732370005831141,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.8599723838476716,"respan/span-02":0.66811585,"typesafe/jev-1.13":0.81,"JEV-27B-VL (10 frames)":0.9081624869250897,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.12890625}},{"suite":"unseen","id":"rbm-ood/usc_koch/678b2d21-3e27-41a4-88a6-0d8a39d58a5e","task":"Separate the purple and orange cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"678b2d21-3e27-41a4-88a6-0d8a39d58a5e","predictions":{"RoboJev-27B":0.9240676274812566,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.9513316588768514,"TypeSafe Jev 1.14":0.85,"Perplexity Decider":0.9394312259308227,"Liquid D1":0.9937100985616374,"Mercury Decide":0.9924227582839227,"Cloudflare Clef":0.8925,"cloudflare/clef-flash":0.7911,"cloudflare/clef-omni":0.3072,"liquid/d1-ultra":0.7830419120902063,"open/intern-decision-4b":0.7318060856600669,"open/robojev-27b-v1@0.5":0.9817926496809816,"open/robojev-27b":null,"open/robojev-4b-v2":0.9838116528624721,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.8914136750138096,"open/robojev-4b-v3@0.75":0.697059291955579,"open/robojev-4b-v3":0.3929848669324905,"openai/gpt-6-luna-decisions":0.88,"perplexity/pplx-decider-flash-v1.2":0.8899940304487899,"respan/span-02":0.7709344,"typesafe/jev-1.13":0.84,"JEV-27B-VL (10 frames)":0.90829807829552,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0419921875}},{"suite":"unseen","id":"rbm-ood/usc_koch/6b399eea-7a64-47ee-acb4-cce20dcea553","task":"Separate the purple and red cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"6b399eea-7a64-47ee-acb4-cce20dcea553","predictions":{"RoboJev-27B":0.9079950370412211,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.8555714482844365,"TypeSafe Jev 1.14":0.88,"Perplexity Decider":0.9107063348108889,"Liquid D1":0.9908743641603485,"Mercury Decide":0.9902915244407818,"Cloudflare Clef":0.8679,"cloudflare/clef-flash":0.7701,"cloudflare/clef-omni":0.173,"liquid/d1-ultra":0.8071467655778203,"open/intern-decision-4b":0.8089141677995819,"open/robojev-27b-v1@0.5":0.9506584292215094,"open/robojev-27b":null,"open/robojev-4b-v2":0.2998075748777713,"open/robojev-4b-v3@0.25":0.957912266254425,"open/robojev-4b-v3@0.5":0.961715889902337,"open/robojev-4b-v3@0.75":0.9198621986336036,"open/robojev-4b-v3":0.870137379491907,"openai/gpt-6-luna-decisions":0.97,"perplexity/pplx-decider-flash-v1.2":0.9105275300211998,"respan/span-02":0.84682035,"typesafe/jev-1.13":0.89,"JEV-27B-VL (10 frames)":0.9135325932650648,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.059326171875}},{"suite":"unseen","id":"rbm-ood/usc_koch/700cbb25-27e3-4b65-ad81-502204b34071","task":"Move the orange cup from right to left","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"700cbb25-27e3-4b65-ad81-502204b34071","predictions":{"RoboJev-27B":0.1946608365607894,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":0.2112642834425615,"TypeSafe Jev 1.14":0.41,"Perplexity Decider":0.21256410271392942,"Liquid D1":0.8519527982093668,"Mercury Decide":0.05340333507274787,"Cloudflare Clef":0.697,"cloudflare/clef-flash":0.2022,"cloudflare/clef-omni":0.2696,"liquid/d1-ultra":0.6325127183904117,"open/intern-decision-4b":0.6229063460425425,"open/robojev-27b-v1@0.5":0.01987159680774069,"open/robojev-27b":null,"open/robojev-4b-v2":0.003927901641619978,"open/robojev-4b-v3@0.25":0.8670357465744019,"open/robojev-4b-v3@0.5":0.21151967170194583,"open/robojev-4b-v3@0.75":0.1295704729794557,"open/robojev-4b-v3":0.047919347698515906,"openai/gpt-6-luna-decisions":0.9,"perplexity/pplx-decider-flash-v1.2":0.14614971570226173,"respan/span-02":0.45523477,"typesafe/jev-1.13":0.21,"JEV-27B-VL (10 frames)":0.16101927082574086,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.146484375}},{"suite":"unseen","id":"rbm-ood/usc_koch/7af3dd22-3db0-4426-938b-47ec12c1e667","task":"Move the orange cup from right to left","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"7af3dd22-3db0-4426-938b-47ec12c1e667","predictions":{"RoboJev-27B":0.9368636672662394,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8526926456282745,"TypeSafe Jev 1.14":0.73,"Perplexity Decider":0.9123587915100706,"Liquid D1":0.9796676461379141,"Mercury Decide":0.9740426416719393,"Cloudflare Clef":0.8828,"cloudflare/clef-flash":0.8937,"cloudflare/clef-omni":0.3493,"liquid/d1-ultra":0.9021558237277519,"open/intern-decision-4b":0.7064759712765732,"open/robojev-27b-v1@0.5":0.964469933484883,"open/robojev-27b":null,"open/robojev-4b-v2":0.2003788035719567,"open/robojev-4b-v3@0.25":0.9820137619972229,"open/robojev-4b-v3@0.5":0.9894338107727867,"open/robojev-4b-v3@0.75":0.9741927167604716,"open/robojev-4b-v3":0.9411294126132068,"openai/gpt-6-luna-decisions":0.82,"perplexity/pplx-decider-flash-v1.2":0.9423306875987949,"respan/span-02":0.7587682,"typesafe/jev-1.13":0.85,"JEV-27B-VL (10 frames)":0.8624835753083376,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.490234375}},{"suite":"unseen","id":"rbm-ood/usc_koch/7b5064ae-99eb-40ac-92e1-461eaf68f42f","task":"Separate the red and orange cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"7b5064ae-99eb-40ac-92e1-461eaf68f42f","predictions":{"RoboJev-27B":0.9489589219048495,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.9551077382017339,"TypeSafe Jev 1.14":0.74,"Perplexity Decider":0.9295299751462661,"Liquid D1":0.9928785728346925,"Mercury Decide":0.9964063975119536,"Cloudflare Clef":0.8599,"cloudflare/clef-flash":0.833,"cloudflare/clef-omni":0.2335,"liquid/d1-ultra":0.8613434807116357,"open/intern-decision-4b":0.778122175998967,"open/robojev-27b-v1@0.5":0.9643568171162639,"open/robojev-27b":null,"open/robojev-4b-v2":0.21506799585334685,"open/robojev-4b-v3@0.25":0.9149009585380554,"open/robojev-4b-v3@0.5":0.8631975135960346,"open/robojev-4b-v3@0.75":0.5883486159258515,"open/robojev-4b-v3":0.2322495721973338,"openai/gpt-6-luna-decisions":0.67,"perplexity/pplx-decider-flash-v1.2":0.8855698310360517,"respan/span-02":0.47474435,"typesafe/jev-1.13":0.83,"JEV-27B-VL (10 frames)":0.8897255026499806,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.08740234375}},{"suite":"unseen","id":"rbm-ood/usc_koch/7d6947fd-1a74-4d77-852e-c2c9b465b95a","task":"Open the blue trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"7d6947fd-1a74-4d77-852e-c2c9b465b95a","predictions":{"RoboJev-27B":0.9306355615031392,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8997911640795737,"TypeSafe Jev 1.14":0.85,"Perplexity Decider":0.9206976376120657,"Liquid D1":0.7772998663336157,"Mercury Decide":0.9924227574084995,"Cloudflare Clef":0.8525,"cloudflare/clef-flash":0.3421,"cloudflare/clef-omni":0.287,"liquid/d1-ultra":0.9552384302845913,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.986152751557608,"open/robojev-27b":null,"open/robojev-4b-v2":0.04392481517503748,"open/robojev-4b-v3@0.25":0.3775406777858734,"open/robojev-4b-v3@0.5":0.24630430768454536,"open/robojev-4b-v3@0.75":0.1050005837572588,"open/robojev-4b-v3":0.08383818708105521,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.3588749004236623,"respan/span-02":0.115586415,"typesafe/jev-1.13":0.64,"JEV-27B-VL (10 frames)":0.845856009877912,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01361083984375}},{"suite":"unseen","id":"rbm-ood/usc_koch/7e6acdf7-1393-4cd0-8de1-cc4fe7590380","task":"Move the orange cup from right to left","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"7e6acdf7-1393-4cd0-8de1-cc4fe7590380","predictions":{"RoboJev-27B":0.9177912134249152,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8761142101116012,"TypeSafe Jev 1.14":0.63,"Perplexity Decider":0.9314365664044794,"Liquid D1":0.9706877691426479,"Mercury Decide":0.9525741286736912,"Cloudflare Clef":0.8615,"cloudflare/clef-flash":0.8731,"cloudflare/clef-omni":0.32,"liquid/d1-ultra":0.8781030334443671,"open/intern-decision-4b":0.637525577991227,"open/robojev-27b-v1@0.5":0.9475113416889918,"open/robojev-27b":null,"open/robojev-4b-v2":0.9241418190100563,"open/robojev-4b-v3@0.25":0.9740425944328308,"open/robojev-4b-v3@0.5":0.9797982783850208,"open/robojev-4b-v3@0.75":0.948664203960477,"open/robojev-4b-v3":0.9241418172849298,"openai/gpt-6-luna-decisions":0.34,"perplexity/pplx-decider-flash-v1.2":0.9413394329981817,"respan/span-02":0.6227286,"typesafe/jev-1.13":0.81,"JEV-27B-VL (10 frames)":0.8726524106177163,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.4375}},{"suite":"unseen","id":"rbm-ood/usc_koch/7f68f4e1-949a-44fd-ace0-d2fc23cff087","task":"Open the red trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"7f68f4e1-949a-44fd-ace0-d2fc23cff087","predictions":{"RoboJev-27B":0.035414137886053604,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.04553687902278685,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.12157851707359409,"Liquid D1":0.24508501864634827,"Mercury Decide":0.02033235430730904,"Cloudflare Clef":0.2935,"cloudflare/clef-flash":0.2813,"cloudflare/clef-omni":0.1335,"liquid/d1-ultra":0.10691173965049809,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.002923435486977096,"open/robojev-27b":null,"open/robojev-4b-v2":0.016188347137528064,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.020201721614979237,"open/robojev-4b-v3@0.75":0.01011736424150334,"open/robojev-4b-v3":0.009249319533522623,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.15688339096328302,"respan/span-02":0.18319172,"typesafe/jev-1.13":0.18,"JEV-27B-VL (10 frames)":0.19787033910173496,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00186920166015625}},{"suite":"unseen","id":"rbm-ood/usc_koch/825b35e5-08a7-4f2d-9a57-f2d7a5d3457a","task":"Move the orange cup from left to right","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"825b35e5-08a7-4f2d-9a57-f2d7a5d3457a","predictions":{"RoboJev-27B":0.010223958629158232,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0021650250962225856,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.028747364768892676,"Liquid D1":0.0033766127578311444,"Mercury Decide":0.0013250224504876423,"Cloudflare Clef":0.0879,"cloudflare/clef-flash":0.1281,"cloudflare/clef-omni":0.1861,"liquid/d1-ultra":0.08946860498786806,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":0.00024738582937222365,"open/robojev-27b":null,"open/robojev-4b-v2":0.005604465165684275,"open/robojev-4b-v3@0.25":0.014063626527786255,"open/robojev-4b-v3@0.5":0.009900079472737449,"open/robojev-4b-v3@0.75":0.010731211960485985,"open/robojev-4b-v3":0.012769726034700673,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.05017535278495343,"respan/span-02":0.13214882,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.0044388384588761355,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00145721435546875}},{"suite":"unseen","id":"rbm-ood/usc_koch/82e7242b-bfcc-416e-be0c-6e46ee0becb5","task":"Open the green trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"82e7242b-bfcc-416e-be0c-6e46ee0becb5","predictions":{"RoboJev-27B":0.0012493963218263768,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":2.9587606905041346e-05,"TypeSafe Jev 1.14":0.02,"Perplexity Decider":0.011826141741194014,"Liquid D1":0.0013250224960860068,"Mercury Decide":0.0011695101562637707,"Cloudflare Clef":0.0444,"cloudflare/clef-flash":0.1407,"cloudflare/clef-omni":0.1277,"liquid/d1-ultra":0.040724815915821534,"open/intern-decision-4b":0.08937422170979005,"open/robojev-27b-v1@0.5":1.1184247730509646e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.10087862681469857,"open/robojev-4b-v3@0.25":0.014063626527786255,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.003927901618504033,"open/robojev-4b-v3":0.003897642342744068,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.04837875069178941,"respan/span-02":0.10128677,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":8.56629616865021e-06,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000732421875}},{"suite":"unseen","id":"rbm-ood/usc_koch/83f1b266-7b3a-4104-8122-2f9e99ab60e2","task":"Separate the red and orange cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"83f1b266-7b3a-4104-8122-2f9e99ab60e2","predictions":{"RoboJev-27B":0.42166397213359297,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.6983198051622261,"TypeSafe Jev 1.14":0.78,"Perplexity Decider":0.7499799760236674,"Liquid D1":0.731058584489497,"Mercury Decide":0.9525741232882133,"Cloudflare Clef":0.7277,"cloudflare/clef-flash":0.761,"cloudflare/clef-omni":0.3491,"liquid/d1-ultra":0.6325127074476208,"open/intern-decision-4b":0.6659927647326706,"open/robojev-27b-v1@0.5":0.6672027605436418,"open/robojev-27b":null,"open/robojev-4b-v2":0.8720986012807731,"open/robojev-4b-v3@0.25":0.9046505093574524,"open/robojev-4b-v3@0.5":0.8848796562508825,"open/robojev-4b-v3@0.75":0.7094794355493901,"open/robojev-4b-v3":0.48641638460333464,"openai/gpt-6-luna-decisions":0.93,"perplexity/pplx-decider-flash-v1.2":0.79088478843454,"respan/span-02":0.25315353,"typesafe/jev-1.13":0.71,"JEV-27B-VL (10 frames)":0.6280244377395067,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.22265625}},{"suite":"unseen","id":"rbm-ood/usc_koch/84484d2d-5cfa-4e80-9e4c-fd9657fb5bb1","task":"Separate the red and orange cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"84484d2d-5cfa-4e80-9e4c-fd9657fb5bb1","predictions":{"RoboJev-27B":0.8499318533477823,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.7924827281261546,"TypeSafe Jev 1.14":0.81,"Perplexity Decider":0.9179659721729613,"Liquid D1":0.9740426421428827,"Mercury Decide":0.957912274487423,"Cloudflare Clef":0.8403,"cloudflare/clef-flash":0.7303,"cloudflare/clef-omni":0.191,"liquid/d1-ultra":0.8832890687087779,"open/intern-decision-4b":0.778122175998967,"open/robojev-27b-v1@0.5":0.8611699826883168,"open/robojev-27b":null,"open/robojev-4b-v2":0.9738159388803848,"open/robojev-4b-v3@0.25":0.9626730680465698,"open/robojev-4b-v3@0.5":0.9640659266906685,"open/robojev-4b-v3@0.75":0.9392374795976737,"open/robojev-4b-v3":0.9118918620554844,"openai/gpt-6-luna-decisions":0.98,"perplexity/pplx-decider-flash-v1.2":0.7728194516694096,"respan/span-02":0.8660069,"typesafe/jev-1.13":0.68,"JEV-27B-VL (10 frames)":0.7599998726758951,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.07373046875}},{"suite":"unseen","id":"rbm-ood/usc_koch/848b7b3f-c3cd-4814-a185-34216025cb90","task":"Move the orange cup from left to right","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"848b7b3f-c3cd-4814-a185-34216025cb90","predictions":{"RoboJev-27B":0.40499249952924515,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.15,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.08896674640754589,"TypeSafe Jev 1.14":0.32,"Perplexity Decider":0.20346028315887685,"Liquid D1":0.7549149923816048,"Mercury Decide":0.007577240224356614,"Cloudflare Clef":0.1562,"cloudflare/clef-flash":0.1744,"cloudflare/clef-omni":0.207,"liquid/d1-ultra":0.4264895951521023,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.05282943589145435,"open/robojev-27b":null,"open/robojev-4b-v2":0.006692850868879798,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.01664357488299338,"open/robojev-4b-v3@0.75":0.02435227726532882,"open/robojev-4b-v3":0.03693826366802302,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.12776661997631006,"respan/span-02":0.14249225,"typesafe/jev-1.13":0.12,"JEV-27B-VL (10 frames)":0.08871940954333479,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00116729736328125}},{"suite":"unseen","id":"rbm-ood/usc_koch/8514edb2-eba2-47f0-bafe-8eba4e21581e","task":"Separate the purple and orange cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"8514edb2-eba2-47f0-bafe-8eba4e21581e","predictions":{"RoboJev-27B":0.9257652642992259,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.9146716309271947,"TypeSafe Jev 1.14":0.87,"Perplexity Decider":0.8702889293522468,"Liquid D1":0.9324533013520764,"Mercury Decide":0.9902915238408678,"Cloudflare Clef":0.7401,"cloudflare/clef-flash":0.7118,"cloudflare/clef-omni":0.2156,"liquid/d1-ultra":0.8727197359864042,"open/intern-decision-4b":0.767101934678807,"open/robojev-27b-v1@0.5":0.982789411529722,"open/robojev-27b":null,"open/robojev-4b-v2":0.8267118019830628,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.7884803282980541,"open/robojev-4b-v3@0.75":0.42613961657870814,"open/robojev-4b-v3":0.21343419258585974,"openai/gpt-6-luna-decisions":0.92,"perplexity/pplx-decider-flash-v1.2":0.8429616426298892,"respan/span-02":0.77705973,"typesafe/jev-1.13":0.88,"JEV-27B-VL (10 frames)":0.9179750741402615,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.10693359375}},{"suite":"unseen","id":"rbm-ood/usc_koch/8b16a94c-da02-41e3-855a-683319ac1337","task":"Throw the black marker away in the blue trash can","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"8b16a94c-da02-41e3-855a-683319ac1337","predictions":{"RoboJev-27B":0.2596630143868607,"GPT-6 Astra":0.06,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.032633823329189945,"TypeSafe Jev 1.14":0.31,"Perplexity Decider":0.09793705496827029,"Liquid D1":0.5,"Mercury Decide":0.007577241562002959,"Cloudflare Clef":0.3158,"cloudflare/clef-flash":0.4525,"cloudflare/clef-omni":0.1182,"liquid/d1-ultra":0.05927725297400196,"open/intern-decision-4b":0.36247442200877295,"open/robojev-27b-v1@0.5":0.009298575537003867,"open/robojev-27b":null,"open/robojev-4b-v2":0.41165137351875947,"open/robojev-4b-v3@0.25":0.3486451506614685,"open/robojev-4b-v3@0.5":0.11512034374911738,"open/robojev-4b-v3@0.75":0.04090405663501426,"open/robojev-4b-v3":0.0299371453325719,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.17080278638257343,"respan/span-02":0.12393651,"typesafe/jev-1.13":0.67,"JEV-27B-VL (10 frames)":0.309687598243035,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.07373046875}},{"suite":"unseen","id":"rbm-ood/usc_koch/9297e8f6-4440-40ac-8179-441b4d49c483","task":"Move the orange cup from right to left","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"9297e8f6-4440-40ac-8179-441b4d49c483","predictions":{"RoboJev-27B":0.0233312353471431,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.006229748641464132,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.026234292033715374,"Liquid D1":0.04468086836450484,"Mercury Decide":0.00205074369620832,"Cloudflare Clef":0.1297,"cloudflare/clef-flash":0.1551,"cloudflare/clef-omni":0.184,"liquid/d1-ultra":0.1272802653209475,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.0014203899304176964,"open/robojev-27b":null,"open/robojev-4b-v2":0.005128210097528264,"open/robojev-4b-v3@0.25":0.01243165135383606,"open/robojev-4b-v3@0.5":0.007626874902958847,"open/robojev-4b-v3@0.75":0.008992055872561407,"open/robojev-4b-v3":0.010300413398065098,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.03585624093826147,"respan/span-02":0.110823825,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.01566488529733962,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0006256103515625}},{"suite":"unseen","id":"rbm-ood/usc_koch/98b482ba-5984-4891-b068-69207b5896ee","task":"Separate the purple and orange cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"98b482ba-5984-4891-b068-69207b5896ee","predictions":{"RoboJev-27B":0.7321499253379627,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.624363948378197,"TypeSafe Jev 1.14":0.72,"Perplexity Decider":0.28231732785078817,"Liquid D1":0.9324533088603709,"Mercury Decide":0.851952809486198,"Cloudflare Clef":0.6232,"cloudflare/clef-flash":0.7946,"cloudflare/clef-omni":0.4678,"liquid/d1-ultra":0.6209651888367836,"open/intern-decision-4b":0.8879876242264044,"open/robojev-27b-v1@0.5":0.37223674590126493,"open/robojev-27b":null,"open/robojev-4b-v2":0.8817313360707654,"open/robojev-4b-v3@0.25":0.9820137619972229,"open/robojev-4b-v3@0.5":0.9843996229781946,"open/robojev-4b-v3@0.75":0.978321636049121,"open/robojev-4b-v3":0.963061736331977,"openai/gpt-6-luna-decisions":0.99,"perplexity/pplx-decider-flash-v1.2":0.7424355774854845,"respan/span-02":0.669672,"typesafe/jev-1.13":0.81,"JEV-27B-VL (10 frames)":0.47195178961730355,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.051025390625}},{"suite":"unseen","id":"rbm-ood/usc_koch/997e4ad9-3b89-4254-86e8-7524534ac12e","task":"Move the orange cup from left to right","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"997e4ad9-3b89-4254-86e8-7524534ac12e","predictions":{"RoboJev-27B":0.7779296908297161,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.557453014194743,"TypeSafe Jev 1.14":0.52,"Perplexity Decider":0.731110045296287,"Liquid D1":0.8354835411997897,"Mercury Decide":0.7310585786300049,"Cloudflare Clef":0.3623,"cloudflare/clef-flash":0.7683,"cloudflare/clef-omni":0.2236,"liquid/d1-ultra":0.620965166675604,"open/intern-decision-4b":0.6932998143038492,"open/robojev-27b-v1@0.5":0.8770351806059072,"open/robojev-27b":null,"open/robojev-4b-v2":0.2551315027042466,"open/robojev-4b-v3@0.25":0.9465966820716858,"open/robojev-4b-v3@0.5":0.9368711827232762,"open/robojev-4b-v3@0.75":0.9320774407500154,"open/robojev-4b-v3":0.9202429190773747,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.2566763890199942,"respan/span-02":0.6115223,"typesafe/jev-1.13":0.38,"JEV-27B-VL (10 frames)":0.6534686098682995,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.421875}},{"suite":"unseen","id":"rbm-ood/usc_koch/9c1ce8e5-06eb-48ae-9a2a-fedf04db52d6","task":"Open the blue trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"9c1ce8e5-06eb-48ae-9a2a-fedf04db52d6","predictions":{"RoboJev-27B":0.01963768865648221,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.06,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.013825963875781761,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.03642183901753011,"Liquid D1":0.26894141551050293,"Mercury Decide":0.009708477144065794,"Cloudflare Clef":0.2841,"cloudflare/clef-flash":0.3293,"cloudflare/clef-omni":0.1207,"liquid/d1-ultra":0.11171743761753893,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.00253925010026784,"open/robojev-27b":null,"open/robojev-4b-v2":0.03544887275269872,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.017755273617510888,"open/robojev-4b-v3@0.75":0.01011736424150334,"open/robojev-4b-v3":0.007868747659394765,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.12082040679982328,"respan/span-02":0.117265366,"typesafe/jev-1.13":0.21,"JEV-27B-VL (10 frames)":0.03050248958968014,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00116729736328125}},{"suite":"unseen","id":"rbm-ood/usc_koch/9dbf386f-4f8f-478c-a1b7-c82d5824ecbc","task":"Separate the purple and orange cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"9dbf386f-4f8f-478c-a1b7-c82d5824ecbc","predictions":{"RoboJev-27B":0.8699933322045535,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8602653815839746,"TypeSafe Jev 1.14":0.8,"Perplexity Decider":0.954654376305783,"Liquid D1":0.9783846672373524,"Mercury Decide":0.9770226275392417,"Cloudflare Clef":0.6996,"cloudflare/clef-flash":0.8043,"cloudflare/clef-omni":0.2368,"liquid/d1-ultra":0.7382047509865145,"open/intern-decision-4b":0.7318060856600669,"open/robojev-27b-v1@0.5":0.9591519360304661,"open/robojev-27b":null,"open/robojev-4b-v2":0.9479346405757522,"open/robojev-4b-v3@0.25":0.9740425944328308,"open/robojev-4b-v3@0.5":0.9784541229757918,"open/robojev-4b-v3@0.75":0.9756477227346713,"open/robojev-4b-v3":0.9649471836741528,"openai/gpt-6-luna-decisions":0.99,"perplexity/pplx-decider-flash-v1.2":0.8291092662960611,"respan/span-02":0.15397605,"typesafe/jev-1.13":0.7,"JEV-27B-VL (10 frames)":0.6775687033900766,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0267333984375}},{"suite":"unseen","id":"rbm-ood/usc_koch/a21e3d03-514c-4074-9de6-808b45be72ac","task":"Open the red trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"a21e3d03-514c-4074-9de6-808b45be72ac","predictions":{"RoboJev-27B":0.01748970844882314,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.008556025543016894,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.03128548944278825,"Liquid D1":0.16451645880021026,"Mercury Decide":0.0031726830987364387,"Cloudflare Clef":0.3047,"cloudflare/clef-flash":0.2909,"cloudflare/clef-omni":0.1082,"liquid/d1-ultra":0.17794900662645483,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.0016110755141650846,"open/robojev-27b":null,"open/robojev-4b-v2":0.012431651137415392,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.01203420913122135,"open/robojev-4b-v3@0.75":0.005604465074944334,"open/robojev-4b-v3":0.0053922199218183735,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.15882484599176477,"respan/span-02":0.10986366,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.029552886448550964,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.001068115234375}},{"suite":"unseen","id":"rbm-ood/usc_koch/a3571be2-f4a8-4ea3-8f54-1fa4733e6e73","task":"Open the green trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"a3571be2-f4a8-4ea3-8f54-1fa4733e6e73","predictions":{"RoboJev-27B":0.8935389973111526,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":0.8536574746018434,"TypeSafe Jev 1.14":0.4,"Perplexity Decider":0.6717572486913806,"Liquid D1":0.754914997895581,"Mercury Decide":0.9859363738090501,"Cloudflare Clef":0.8626,"cloudflare/clef-flash":0.4781,"cloudflare/clef-omni":0.2541,"liquid/d1-ultra":0.8930882547306663,"open/intern-decision-4b":0.637525577991227,"open/robojev-27b-v1@0.5":0.9828142202757398,"open/robojev-27b":null,"open/robojev-4b-v2":0.0893637337766288,"open/robojev-4b-v3@0.25":0.8933094143867493,"open/robojev-4b-v3@0.5":0.7284637291157656,"open/robojev-4b-v3@0.75":0.7333927218765676,"open/robojev-4b-v3":0.6815425035280747,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.8060030173747186,"respan/span-02":0.42542073,"typesafe/jev-1.13":0.44,"JEV-27B-VL (10 frames)":0.8240501238644417,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0634765625}},{"suite":"unseen","id":"rbm-ood/usc_koch/a4c50b45-4262-491b-9333-aa2628454c58","task":"Open the blue trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"a4c50b45-4262-491b-9333-aa2628454c58","predictions":{"RoboJev-27B":0.9683970734473736,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.9491468034855927,"TypeSafe Jev 1.14":0.89,"Perplexity Decider":0.9454317526404628,"Liquid D1":0.9648551551150879,"Mercury Decide":0.9959298629692994,"Cloudflare Clef":0.8877,"cloudflare/clef-flash":0.8073,"cloudflare/clef-omni":0.3137,"liquid/d1-ultra":0.9734966361862298,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.9933391186354554,"open/robojev-27b":null,"open/robojev-4b-v2":0.9069361009827602,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.9879657908687787,"open/robojev-4b-v3@0.75":0.9856023867504186,"open/robojev-4b-v3":0.9833095447847391,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.9122498367519789,"respan/span-02":0.8159261,"typesafe/jev-1.13":0.63,"JEV-27B-VL (10 frames)":0.9401901790188544,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.007110595703125}},{"suite":"unseen","id":"rbm-ood/usc_koch/a65d04c6-cef3-40b8-97a1-f811dfabd609","task":"Open the blue trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"a65d04c6-cef3-40b8-97a1-f811dfabd609","predictions":{"RoboJev-27B":0.5572801791816784,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.0003441824569463154,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.01632830634036804,"Liquid D1":0.06754669489377622,"Mercury Decide":0.0006667024352052932,"Cloudflare Clef":0.2533,"cloudflare/clef-flash":0.2598,"cloudflare/clef-omni":0.1018,"liquid/d1-ultra":0.15087379195063033,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.00032557123108843433,"open/robojev-27b":null,"open/robojev-4b-v2":0.027346786441616523,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.01203420913122135,"open/robojev-4b-v3@0.75":0.008992055872561407,"open/robojev-4b-v3":0.007064018099624773,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.13460585789874424,"respan/span-02":0.5810548,"typesafe/jev-1.13":0.27,"JEV-27B-VL (10 frames)":0.3596960303606616,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0037078857421875}},{"suite":"unseen","id":"rbm-ood/usc_koch/a670ad76-0983-4b9a-b59a-6d4f76bb29fa","task":"Separate the red and orange cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"a670ad76-0983-4b9a-b59a-6d4f76bb29fa","predictions":{"RoboJev-27B":0.8566846765719073,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.8903945025431597,"TypeSafe Jev 1.14":0.64,"Perplexity Decider":0.9097656374080367,"Liquid D1":0.9669140192277585,"Mercury Decide":0.9890130558210519,"Cloudflare Clef":0.8499,"cloudflare/clef-flash":0.6342,"cloudflare/clef-omni":0.1909,"liquid/d1-ultra":0.774538396275708,"open/intern-decision-4b":0.8363317223730603,"open/robojev-27b-v1@0.5":0.9640779219853784,"open/robojev-27b":null,"open/robojev-4b-v2":0.6811210474999878,"open/robojev-4b-v3@0.25":0.4073334336280823,"open/robojev-4b-v3@0.5":0.1804712758005596,"open/robojev-4b-v3@0.75":0.09953688489563063,"open/robojev-4b-v3":0.07585818271507015,"openai/gpt-6-luna-decisions":0.93,"perplexity/pplx-decider-flash-v1.2":0.803416711796172,"respan/span-02":0.33603385,"typesafe/jev-1.13":0.75,"JEV-27B-VL (10 frames)":0.8568881676727441,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.046142578125}},{"suite":"unseen","id":"rbm-ood/usc_koch/a80e0d43-99e8-432f-ac92-865377371225","task":"Separate the red and orange cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"a80e0d43-99e8-432f-ac92-865377371225","predictions":{"RoboJev-27B":0.9035225924745173,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.8955465585088046,"TypeSafe Jev 1.14":0.76,"Perplexity Decider":0.935257726664504,"Liquid D1":0.9324533069832973,"Mercury Decide":0.989013055851412,"Cloudflare Clef":0.8242,"cloudflare/clef-flash":0.7683,"cloudflare/clef-omni":0.2464,"liquid/d1-ultra":0.8553419909260974,"open/intern-decision-4b":0.844739173437523,"open/robojev-27b-v1@0.5":0.9690406931295851,"open/robojev-27b":null,"open/robojev-4b-v2":0.8564010365978134,"open/robojev-4b-v3@0.25":0.9046505093574524,"open/robojev-4b-v3@0.5":0.846904551172507,"open/robojev-4b-v3@0.75":0.6168479107609087,"open/robojev-4b-v3":0.2953447966522927,"openai/gpt-6-luna-decisions":0.88,"perplexity/pplx-decider-flash-v1.2":0.8390723960058508,"respan/span-02":0.6113145,"typesafe/jev-1.13":0.8,"JEV-27B-VL (10 frames)":0.866351638545653,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.048095703125}},{"suite":"unseen","id":"rbm-ood/usc_koch/a9adf6ac-ad21-4ee8-93aa-f8cd609daa6a","task":"Separate the purple and orange cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"a9adf6ac-ad21-4ee8-93aa-f8cd609daa6a","predictions":{"RoboJev-27B":0.8670008181220603,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.6580138066080802,"TypeSafe Jev 1.14":0.82,"Perplexity Decider":0.8248452230794917,"Liquid D1":0.9783846661343925,"Mercury Decide":0.9465966726483187,"Cloudflare Clef":0.8257,"cloudflare/clef-flash":0.7295,"cloudflare/clef-omni":0.197,"liquid/d1-ultra":0.7658012573170664,"open/intern-decision-4b":0.8363317223730603,"open/robojev-27b-v1@0.5":0.8856518691074062,"open/robojev-27b":null,"open/robojev-4b-v2":0.7185943895092446,"open/robojev-4b-v3@0.25":0.9669140577316284,"open/robojev-4b-v3@0.5":0.9565659184411002,"open/robojev-4b-v3@0.75":0.9198621986336036,"open/robojev-4b-v3":0.863871653255755,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.7863920703896742,"respan/span-02":0.33081242,"typesafe/jev-1.13":0.73,"JEV-27B-VL (10 frames)":0.7293664361517632,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0203857421875}},{"suite":"unseen","id":"rbm-ood/usc_koch/ada56406-a1c2-4228-bfc7-0f2d6c877ed7","task":"Throw the orange cup away in the red trash can","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"ada56406-a1c2-4228-bfc7-0f2d6c877ed7","predictions":{"RoboJev-27B":0.011288716785091914,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.05101653815978637,"TypeSafe Jev 1.14":0.44,"Perplexity Decider":0.07254781612936663,"Liquid D1":0.32082130082460697,"Mercury Decide":0.025957356868136584,"Cloudflare Clef":0.3894,"cloudflare/clef-flash":0.4577,"cloudflare/clef-omni":0.1027,"liquid/d1-ultra":0.09784417627224803,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.008605381545532755,"open/robojev-27b":null,"open/robojev-4b-v2":0.00731334505501762,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.02154587702420825,"open/robojev-4b-v3@0.75":0.028975397327291364,"open/robojev-4b-v3":0.05593065484668503,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1280944791872773,"respan/span-02":0.08250829,"typesafe/jev-1.13":0.21,"JEV-27B-VL (10 frames)":0.04262152374875406,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0078125}},{"suite":"unseen","id":"rbm-ood/usc_koch/ae9e0f4c-57e4-4b1a-affe-127dca818414","task":"Throw the black marker away in the blue trash can","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"ae9e0f4c-57e4-4b1a-affe-127dca818414","predictions":{"RoboJev-27B":0.665865571454271,"GPT-6 Astra":0.78,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.1472480671458033,"TypeSafe Jev 1.14":0.54,"Perplexity Decider":0.2083946954592602,"Liquid D1":0.5621765008857981,"Mercury Decide":0.022977368111968415,"Cloudflare Clef":0.3366,"cloudflare/clef-flash":0.4351,"cloudflare/clef-omni":0.092,"liquid/d1-ultra":0.4386055069579756,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.010953512620091827,"open/robojev-27b":null,"open/robojev-4b-v2":0.01929224350793923,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.07137286741841814,"open/robojev-4b-v3@0.75":0.0717892678456694,"open/robojev-4b-v3":0.0721349360304201,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.16015453080839756,"respan/span-02":0.10366052,"typesafe/jev-1.13":0.51,"JEV-27B-VL (10 frames)":0.6096990647189805,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0191650390625}},{"suite":"unseen","id":"rbm-ood/usc_koch/aed484f3-5e85-49e1-bd49-7eadce0fdb29","task":"Throw the orange cup away in the red trash can","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"aed484f3-5e85-49e1-bd49-7eadce0fdb29","predictions":{"RoboJev-27B":0.011492164017890407,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.0038884100008619235,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.02351878074645125,"Liquid D1":0.2018132270610754,"Mercury Decide":0.004905406310353991,"Cloudflare Clef":0.0862,"cloudflare/clef-flash":0.3529,"cloudflare/clef-omni":0.0705,"liquid/d1-ultra":0.13286530955437229,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.0022342374490307917,"open/robojev-27b":null,"open/robojev-4b-v2":0.006402505190256269,"open/robojev-4b-v3@0.25":0.03308597952127457,"open/robojev-4b-v3@0.5":0.011276606158891207,"open/robojev-4b-v3@0.75":0.008992055872561407,"open/robojev-4b-v3":0.008764341864947102,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.03478622187066964,"respan/span-02":0.07793482,"typesafe/jev-1.13":0.09,"JEV-27B-VL (10 frames)":0.00600787928227621,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0023193359375}},{"suite":"unseen","id":"rbm-ood/usc_koch/b1224526-a8c1-4bc8-ba54-f80e5f6aa33c","task":"Open the blue trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"b1224526-a8c1-4bc8-ba54-f80e5f6aa33c","predictions":{"RoboJev-27B":0.7748354115102231,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.7220881974674989,"TypeSafe Jev 1.14":0.85,"Perplexity Decider":0.6514802490977244,"Liquid D1":0.8354835411997897,"Mercury Decide":0.974042641483562,"Cloudflare Clef":0.789,"cloudflare/clef-flash":0.4017,"cloudflare/clef-omni":0.442,"liquid/d1-ultra":0.9287049368679837,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.9331320853866472,"open/robojev-27b":null,"open/robojev-4b-v2":0.2003788035719567,"open/robojev-4b-v3@0.25":0.7981867790222168,"open/robojev-4b-v3@0.5":0.741279894904784,"open/robojev-4b-v3@0.75":0.2905205644506098,"open/robojev-4b-v3":0.20445237038006636,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.4513501216186701,"respan/span-02":0.2130023,"typesafe/jev-1.13":0.5,"JEV-27B-VL (10 frames)":0.6563733408308122,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00628662109375}},{"suite":"unseen","id":"rbm-ood/usc_koch/b1f1ebcd-adc3-42f8-9a3b-f393f473b269","task":"Throw the orange cup away in the red trash can","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"b1f1ebcd-adc3-42f8-9a3b-f393f473b269","predictions":{"RoboJev-27B":0.9572640427717793,"GPT-6 Astra":0.93,"GPT-6.1 Sol":0.92,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.9071759818077237,"TypeSafe Jev 1.14":0.59,"Perplexity Decider":0.9635069547251017,"Liquid D1":0.9626731137267751,"Mercury Decide":0.9984988176364701,"Cloudflare Clef":0.7842,"cloudflare/clef-flash":0.6401,"cloudflare/clef-omni":0.1546,"liquid/d1-ultra":0.7830419120902063,"open/intern-decision-4b":0.7557061813028185,"open/robojev-27b-v1@0.5":0.9865595784034619,"open/robojev-27b":null,"open/robojev-4b-v2":0.017673504996080332,"open/robojev-4b-v3@0.25":0.8933094143867493,"open/robojev-4b-v3@0.5":0.7152565465994749,"open/robojev-4b-v3@0.75":0.6713474489845783,"open/robojev-4b-v3":0.7955476296199337,"openai/gpt-6-luna-decisions":0.86,"perplexity/pplx-decider-flash-v1.2":0.4899767953836534,"respan/span-02":0.122140266,"typesafe/jev-1.13":0.79,"JEV-27B-VL (10 frames)":0.9179683217823239,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0289306640625}},{"suite":"unseen","id":"rbm-ood/usc_koch/b2c8a625-3de1-4da2-a704-b50ca0cbd6af","task":"Throw the black marker away in the blue trash can","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"b2c8a625-3de1-4da2-a704-b50ca0cbd6af","predictions":{"RoboJev-27B":0.2537769228538908,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.78,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.6315615372220431,"TypeSafe Jev 1.14":0.45,"Perplexity Decider":0.6925063445676424,"Liquid D1":0.5926666143433998,"Mercury Decide":0.904650527388829,"Cloudflare Clef":0.5306,"cloudflare/clef-flash":0.5848,"cloudflare/clef-omni":0.0983,"liquid/d1-ultra":0.4876613324012321,"open/intern-decision-4b":0.5777854893190272,"open/robojev-27b-v1@0.5":0.6903448388114657,"open/robojev-27b":null,"open/robojev-4b-v2":0.41165137351875947,"open/robojev-4b-v3@0.25":0.18242551386356354,"open/robojev-4b-v3@0.5":0.06312881727672377,"open/robojev-4b-v3@0.75":0.054313266183183405,"open/robojev-4b-v3":0.07975708092262541,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.44742350958568095,"respan/span-02":0.84481704,"typesafe/jev-1.13":0.53,"JEV-27B-VL (10 frames)":0.2862586246481442,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.004913330078125}},{"suite":"unseen","id":"rbm-ood/usc_koch/b7071bb3-99e1-4af1-82f6-c19bbea69911","task":"Separate the purple and red cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"b7071bb3-99e1-4af1-82f6-c19bbea69911","predictions":{"RoboJev-27B":0.8916637343355458,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.86,"JEV-27B-VL":0.8344137624907007,"TypeSafe Jev 1.14":0.85,"Perplexity Decider":0.9617291664684723,"Liquid D1":0.9908743634866403,"Mercury Decide":0.9770226321389233,"Cloudflare Clef":0.8707,"cloudflare/clef-flash":0.7625,"cloudflare/clef-omni":0.2932,"liquid/d1-ultra":0.7913111224201902,"open/intern-decision-4b":0.799028310455341,"open/robojev-27b-v1@0.5":0.8818968468161434,"open/robojev-27b":null,"open/robojev-4b-v2":0.87699602202752,"open/robojev-4b-v3@0.25":0.9669140577316284,"open/robojev-4b-v3@0.5":0.9537489247538957,"open/robojev-4b-v3@0.75":0.9320774407500154,"open/robojev-4b-v3":0.9202429190773747,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.8957480289864568,"respan/span-02":0.7927095,"typesafe/jev-1.13":0.73,"JEV-27B-VL (10 frames)":0.8341195672207893,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0225830078125}},{"suite":"unseen","id":"rbm-ood/usc_koch/b979938e-e8ac-4342-b3df-308bf7cdc2d7","task":"Separate the red and orange cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"b979938e-e8ac-4342-b3df-308bf7cdc2d7","predictions":{"RoboJev-27B":0.046004381076940215,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.006597773861907531,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.12512947048743361,"Liquid D1":0.5621765008857981,"Mercury Decide":0.025957358610626615,"Cloudflare Clef":0.3256,"cloudflare/clef-flash":0.2542,"cloudflare/clef-omni":0.0763,"liquid/d1-ultra":0.06502831803896442,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.00672063400999484,"open/robojev-27b":null,"open/robojev-4b-v2":0.48884113714168653,"open/robojev-4b-v3@0.25":0.4073334336280823,"open/robojev-4b-v3@0.5":0.21151967170194583,"open/robojev-4b-v3@0.75":0.20277377238617383,"open/robojev-4b-v3":0.19575444983810342,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2822185988128712,"respan/span-02":0.63605464,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.03072238868896382,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0008544921875}},{"suite":"unseen","id":"rbm-ood/usc_koch/bade4079-d263-4f66-afae-22c87b06a3e9","task":"Open the blue trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"bade4079-d263-4f66-afae-22c87b06a3e9","predictions":{"RoboJev-27B":0.8140667874155314,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.8735843772120351,"TypeSafe Jev 1.14":0.78,"Perplexity Decider":0.9113548320193652,"Liquid D1":0.5926665999540697,"Mercury Decide":0.9890130590392009,"Cloudflare Clef":0.7922,"cloudflare/clef-flash":0.5823,"cloudflare/clef-omni":0.3683,"liquid/d1-ultra":0.9105313863830489,"open/intern-decision-4b":0.37709365395745764,"open/robojev-27b-v1@0.5":0.9839467139937087,"open/robojev-27b":null,"open/robojev-4b-v2":0.04392481517503748,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.04343408155889982,"open/robojev-4b-v3@0.75":0.02297736967873775,"open/robojev-4b-v3":0.017606235547797083,"openai/gpt-6-luna-decisions":0.98,"perplexity/pplx-decider-flash-v1.2":0.29055802754761406,"respan/span-02":0.8714319,"typesafe/jev-1.13":0.46,"JEV-27B-VL (10 frames)":0.804786526360711,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0267333984375}},{"suite":"unseen","id":"rbm-ood/usc_koch/c3589188-8b59-462e-ba1e-23183b5608da","task":"Open the green trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"c3589188-8b59-462e-ba1e-23183b5608da","predictions":{"RoboJev-27B":0.8384697228075328,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.82,"JEV-27B-VL":0.8189731142303946,"TypeSafe Jev 1.14":0.43,"Perplexity Decider":0.521203430028318,"Liquid D1":0.6224593312018546,"Mercury Decide":0.9324533079218341,"Cloudflare Clef":0.8101,"cloudflare/clef-flash":0.3643,"cloudflare/clef-omni":0.4577,"liquid/d1-ultra":0.9021558237277519,"open/intern-decision-4b":0.5313278281391198,"open/robojev-27b-v1@0.5":0.9529825755468051,"open/robojev-27b":null,"open/robojev-4b-v2":0.0790476748344352,"open/robojev-4b-v3@0.25":0.18242551386356354,"open/robojev-4b-v3@0.5":0.08060089942949411,"open/robojev-4b-v3@0.75":0.06424971259337996,"open/robojev-4b-v3":0.05887058738679302,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.47479431455055043,"respan/span-02":0.94530946,"typesafe/jev-1.13":0.5,"JEV-27B-VL (10 frames)":0.8220859753917392,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0260009765625}},{"suite":"unseen","id":"rbm-ood/usc_koch/cbc83d7d-c80b-46ad-9d78-5991291a78a2","task":"Open the blue trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"cbc83d7d-c80b-46ad-9d78-5991291a78a2","predictions":{"RoboJev-27B":0.19176058396440512,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.25,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.22038816818431406,"TypeSafe Jev 1.14":0.47,"Perplexity Decider":0.12629034636893935,"Liquid D1":0.46879062662624377,"Mercury Decide":0.18242552602881168,"Cloudflare Clef":0.3745,"cloudflare/clef-flash":0.3687,"cloudflare/clef-omni":0.1347,"liquid/d1-ultra":0.25236786828046404,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.0963162257234301,"open/robojev-27b":null,"open/robojev-4b-v2":0.01138187822152329,"open/robojev-4b-v3@0.25":0.03308597952127457,"open/robojev-4b-v3@0.5":0.009275566578748366,"open/robojev-4b-v3@0.75":0.004978582695254881,"open/robojev-4b-v3":0.004584702275672031,"openai/gpt-6-luna-decisions":0.09,"perplexity/pplx-decider-flash-v1.2":0.13562412999102075,"respan/span-02":0.18182124,"typesafe/jev-1.13":0.38,"JEV-27B-VL (10 frames)":0.20269326576354263,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00186920166015625}},{"suite":"unseen","id":"rbm-ood/usc_koch/cca1425f-b52a-43e3-b8c9-ab2f61ce9499","task":"Move the orange cup from left to right","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"cca1425f-b52a-43e3-b8c9-ab2f61ce9499","predictions":{"RoboJev-27B":0.7975781888795566,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8212457286007666,"TypeSafe Jev 1.14":0.71,"Perplexity Decider":0.869994959163728,"Liquid D1":0.9820137918144733,"Mercury Decide":0.9796676452474677,"Cloudflare Clef":0.5043,"cloudflare/clef-flash":0.8644,"cloudflare/clef-omni":0.1962,"liquid/d1-ultra":0.8727197412158103,"open/intern-decision-4b":0.8363317223730603,"open/robojev-27b-v1@0.5":0.9353955281055123,"open/robojev-27b":null,"open/robojev-4b-v2":0.09690095299759889,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.9770226296926641,"open/robojev-4b-v3@0.75":0.9613683489514899,"open/robojev-4b-v3":0.944069345153315,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.9515727545885552,"respan/span-02":0.8204814,"typesafe/jev-1.13":0.86,"JEV-27B-VL (10 frames)":0.8462824116386588,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.7421875}},{"suite":"unseen","id":"rbm-ood/usc_koch/cce54bfa-775a-446e-bad7-4ebd0d4e6428","task":"Move the orange cup from right to left","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"cce54bfa-775a-446e-bad7-4ebd0d4e6428","predictions":{"RoboJev-27B":0.9368237493692095,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.9038817939084939,"TypeSafe Jev 1.14":0.78,"Perplexity Decider":0.9326812035951354,"Liquid D1":0.9859363709422372,"Mercury Decide":0.9706877663867577,"Cloudflare Clef":0.8992,"cloudflare/clef-flash":0.8275,"cloudflare/clef-omni":0.3515,"liquid/d1-ultra":0.9105313959709188,"open/intern-decision-4b":0.6518947636686268,"open/robojev-27b-v1@0.5":0.9628615624639961,"open/robojev-27b":null,"open/robojev-4b-v2":0.48884113714168653,"open/robojev-4b-v3@0.25":0.9820137619972229,"open/robojev-4b-v3@0.5":0.9871579519028945,"open/robojev-4b-v3@0.75":0.9710246026727085,"open/robojev-4b-v3":0.944069345153315,"openai/gpt-6-luna-decisions":0.93,"perplexity/pplx-decider-flash-v1.2":0.9702187091703078,"respan/span-02":0.9039749,"typesafe/jev-1.13":0.84,"JEV-27B-VL (10 frames)":0.8328101529861881,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.59765625}},{"suite":"unseen","id":"rbm-ood/usc_koch/cf7f8d89-b361-47fe-a806-126bf4d62406","task":"Open the red trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"cf7f8d89-b361-47fe-a806-126bf4d62406","predictions":{"RoboJev-27B":0.896558539946594,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.9058706591226002,"TypeSafe Jev 1.14":0.52,"Perplexity Decider":0.8463630494271324,"Liquid D1":0.7981867729389246,"Mercury Decide":0.9820137920776683,"Cloudflare Clef":0.738,"cloudflare/clef-flash":0.4114,"cloudflare/clef-omni":0.3154,"liquid/d1-ultra":0.7745383798334267,"open/intern-decision-4b":0.4069889545588398,"open/robojev-27b-v1@0.5":0.9951774292668637,"open/robojev-27b":null,"open/robojev-4b-v2":0.5445246098935005,"open/robojev-4b-v3@0.25":0.9399133324623108,"open/robojev-4b-v3@0.5":0.9565659184411002,"open/robojev-4b-v3@0.75":0.948664203960477,"open/robojev-4b-v3":0.9241418172849298,"openai/gpt-6-luna-decisions":0.98,"perplexity/pplx-decider-flash-v1.2":0.8641935336553479,"respan/span-02":0.60610086,"typesafe/jev-1.13":0.66,"JEV-27B-VL (10 frames)":0.8659124559449206,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.02294921875}},{"suite":"unseen","id":"rbm-ood/usc_koch/d26a7326-12bd-444e-a621-ec8736184397","task":"Open the green trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"d26a7326-12bd-444e-a621-ec8736184397","predictions":{"RoboJev-27B":0.1148063622898213,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":0.26263107096643634,"TypeSafe Jev 1.14":0.16,"Perplexity Decider":0.16976453526736032,"Liquid D1":0.3208212878370535,"Mercury Decide":0.4378234991142019,"Cloudflare Clef":0.4357,"cloudflare/clef-flash":0.371,"cloudflare/clef-omni":0.1621,"liquid/d1-ultra":0.5,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.25123896375491894,"open/robojev-27b":null,"open/robojev-4b-v2":0.056652424895021994,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.153095448827493,"open/robojev-4b-v3@0.75":0.1167256573155804,"open/robojev-4b-v3":0.24208096504423623,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.4349030445311423,"respan/span-02":0.32474127,"typesafe/jev-1.13":0.29,"JEV-27B-VL (10 frames)":0.25504583436860245,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01495361328125}},{"suite":"unseen","id":"rbm-ood/usc_koch/d56da746-11bc-4c11-8b3d-0f8d4497e24f","task":"Throw the orange cup away in the red trash can","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"d56da746-11bc-4c11-8b3d-0f8d4497e24f","predictions":{"RoboJev-27B":0.0011496709569890852,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.00343911900079967,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.018917054474842952,"Liquid D1":0.08035746882220708,"Mercury Decide":0.002182716307415614,"Cloudflare Clef":0.237,"cloudflare/clef-flash":0.2878,"cloudflare/clef-omni":0.0824,"liquid/d1-ultra":0.06209063474307424,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.00019646915460579136,"open/robojev-27b":null,"open/robojev-4b-v2":0.006402505190256269,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.006692850574775813,"open/robojev-4b-v3@0.75":0.005946149584938689,"open/robojev-4b-v3":0.007868747659394765,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.03341270939686685,"respan/span-02":0.19823807,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.003972635045695472,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000732421875}},{"suite":"unseen","id":"rbm-ood/usc_koch/d7d5bb5c-84a3-4ca5-945a-d3178f9c0f34","task":"Separate the purple and orange cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"d7d5bb5c-84a3-4ca5-945a-d3178f9c0f34","predictions":{"RoboJev-27B":0.9101160464401463,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.8918888492928393,"TypeSafe Jev 1.14":0.81,"Perplexity Decider":0.9186226206349893,"Liquid D1":0.9875683515708102,"Mercury Decide":0.989013054920375,"Cloudflare Clef":0.8794,"cloudflare/clef-flash":0.8209,"cloudflare/clef-omni":0.2228,"liquid/d1-ultra":0.8553419763635007,"open/intern-decision-4b":0.8998738837161642,"open/robojev-27b-v1@0.5":0.9692437827319195,"open/robojev-27b":null,"open/robojev-4b-v2":0.7532592839990138,"open/robojev-4b-v3@0.25":0.970687747001648,"open/robojev-4b-v3@0.5":0.940652165185709,"open/robojev-4b-v3@0.75":0.777299857680221,"open/robojev-4b-v3":0.5,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9278942393626821,"respan/span-02":0.8302883,"typesafe/jev-1.13":0.84,"JEV-27B-VL (10 frames)":0.9214427673928127,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.044677734375}},{"suite":"unseen","id":"rbm-ood/usc_koch/dcaf97d1-1799-4110-9dc1-daeca882e461","task":"Move the orange cup from left to right","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"dcaf97d1-1799-4110-9dc1-daeca882e461","predictions":{"RoboJev-27B":0.8943974214486159,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.7142941616388551,"TypeSafe Jev 1.14":0.77,"Perplexity Decider":0.8622123576008813,"Liquid D1":0.9669140194661121,"Mercury Decide":0.9740426441208441,"Cloudflare Clef":0.5836,"cloudflare/clef-flash":0.8523,"cloudflare/clef-omni":0.2755,"liquid/d1-ultra":0.9349716869700875,"open/intern-decision-4b":0.608060011110835,"open/robojev-27b-v1@0.5":0.9417108624486163,"open/robojev-27b":null,"open/robojev-4b-v2":0.7362922553128872,"open/robojev-4b-v3@0.25":0.977022647857666,"open/robojev-4b-v3@0.5":0.975498409742533,"open/robojev-4b-v3@0.75":0.9541617453379198,"open/robojev-4b-v3":0.9278650639695798,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.9209070090005369,"respan/span-02":0.6035417,"typesafe/jev-1.13":0.73,"JEV-27B-VL (10 frames)":0.8278382933660849,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.69921875}},{"suite":"unseen","id":"rbm-ood/usc_koch/dd8c85b1-a78d-4427-89e7-13389a2452af","task":"Separate the purple and red cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"dd8c85b1-a78d-4427-89e7-13389a2452af","predictions":{"RoboJev-27B":0.9209033167675652,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.9,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":0.8657287190284823,"TypeSafe Jev 1.14":0.89,"Perplexity Decider":0.9447812883409646,"Liquid D1":0.9950945944397532,"Mercury Decide":0.9924227585500511,"Cloudflare Clef":0.8277,"cloudflare/clef-flash":0.7111,"cloudflare/clef-omni":0.1983,"liquid/d1-ultra":0.8426924916319732,"open/intern-decision-4b":0.844739173437523,"open/robojev-27b-v1@0.5":0.9505563287372512,"open/robojev-27b":null,"open/robojev-4b-v2":0.30926207372882397,"open/robojev-4b-v3@0.25":0.977022647857666,"open/robojev-4b-v3@0.5":0.972148766331303,"open/robojev-4b-v3@0.75":0.9320774407500154,"open/robojev-4b-v3":0.8761560328980749,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.9107578554266346,"respan/span-02":0.8777331,"typesafe/jev-1.13":0.85,"JEV-27B-VL (10 frames)":0.9177507990068053,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1240234375}},{"suite":"unseen","id":"rbm-ood/usc_koch/de2eaf57-eb9d-4b9c-a02a-9042cfc89c3f","task":"Separate the purple and red cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"de2eaf57-eb9d-4b9c-a02a-9042cfc89c3f","predictions":{"RoboJev-27B":0.9341071552061002,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.9254217694716486,"TypeSafe Jev 1.14":0.86,"Perplexity Decider":0.9426133681123915,"Liquid D1":0.9859363699608057,"Mercury Decide":0.9859363734732974,"Cloudflare Clef":0.8991,"cloudflare/clef-flash":0.813,"cloudflare/clef-omni":0.3501,"liquid/d1-ultra":0.8360373742354359,"open/intern-decision-4b":0.799028310455341,"open/robojev-27b-v1@0.5":0.9641797058006435,"open/robojev-27b":null,"open/robojev-4b-v2":0.9500944211010165,"open/robojev-4b-v3@0.25":0.977022647857666,"open/robojev-4b-v3@0.5":0.9784541229757918,"open/robojev-4b-v3@0.75":0.9693020651146849,"open/robojev-4b-v3":0.9380451002706788,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9242996500525144,"respan/span-02":0.8705603,"typesafe/jev-1.13":0.91,"JEV-27B-VL (10 frames)":0.9183476933278475,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1259765625}},{"suite":"unseen","id":"rbm-ood/usc_koch/def91146-877c-4277-83c1-741029f542bf","task":"Throw the orange cup away in the red trash can","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"def91146-877c-4277-83c1-741029f542bf","predictions":{"RoboJev-27B":0.9622609111263013,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.9598090523414199,"TypeSafe Jev 1.14":0.54,"Perplexity Decider":0.9718213255305552,"Liquid D1":0.9908743616002569,"Mercury Decide":0.9986749774071715,"Cloudflare Clef":0.8957,"cloudflare/clef-flash":0.7727,"cloudflare/clef-omni":0.1609,"liquid/d1-ultra":0.8781030233661222,"open/intern-decision-4b":0.8275619327448428,"open/robojev-27b-v1@0.5":0.9912768151048479,"open/robojev-27b":null,"open/robojev-4b-v2":0.007644678711335276,"open/robojev-4b-v3@0.25":0.9046505093574524,"open/robojev-4b-v3@0.5":0.549182531250921,"open/robojev-4b-v3@0.75":0.3419172570227415,"open/robojev-4b-v3":0.3929848669324905,"openai/gpt-6-luna-decisions":0.84,"perplexity/pplx-decider-flash-v1.2":0.5276250565343181,"respan/span-02":0.8970788,"typesafe/jev-1.13":0.67,"JEV-27B-VL (10 frames)":0.9620835942593976,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01544189453125}},{"suite":"unseen","id":"rbm-ood/usc_koch/e362ec6b-f1d9-4a00-9a4a-36e783f97dd2","task":"Open the green trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"e362ec6b-f1d9-4a00-9a4a-36e783f97dd2","predictions":{"RoboJev-27B":0.4465671870260898,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.20117936953915216,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.11673559269816358,"Liquid D1":0.1645164628965632,"Mercury Decide":0.5926665999540697,"Cloudflare Clef":0.3418,"cloudflare/clef-flash":0.2912,"cloudflare/clef-omni":0.0631,"liquid/d1-ultra":0.2254616160560029,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.15294294739030329,"open/robojev-27b":null,"open/robojev-4b-v2":0.03251944279343901,"open/robojev-4b-v3@0.25":0.10669060051441193,"open/robojev-4b-v3@0.5":0.02450159025746704,"open/robojev-4b-v3@0.75":0.011381877728436919,"open/robojev-4b-v3":0.006007651396687169,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.277340885763863,"respan/span-02":0.707182,"typesafe/jev-1.13":0.22,"JEV-27B-VL (10 frames)":0.3251860885961696,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00150299072265625}},{"suite":"unseen","id":"rbm-ood/usc_koch/e370fed8-781f-4fb9-87f0-72f2cd492876","task":"Separate the red and orange cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"e370fed8-781f-4fb9-87f0-72f2cd492876","predictions":{"RoboJev-27B":0.70624934401524,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.6934297295057951,"TypeSafe Jev 1.14":0.78,"Perplexity Decider":0.8450672997188566,"Liquid D1":0.9603611611826556,"Mercury Decide":0.9525741274956179,"Cloudflare Clef":0.7376,"cloudflare/clef-flash":0.8707,"cloudflare/clef-omni":0.1557,"liquid/d1-ultra":0.7830419160891692,"open/intern-decision-4b":0.8363317223730603,"open/robojev-27b-v1@0.5":0.7790215709161623,"open/robojev-27b":null,"open/robojev-4b-v2":0.9579122700410143,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.9797982783850208,"open/robojev-4b-v3@0.75":0.9566958954509301,"open/robojev-4b-v3":0.9161618129189448,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.7140321503715807,"respan/span-02":0.7443402,"typesafe/jev-1.13":0.78,"JEV-27B-VL (10 frames)":0.7307860773173114,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.029296875}},{"suite":"unseen","id":"rbm-ood/usc_koch/e517076b-2ed5-4da3-89d0-4a5b2e1d84fa","task":"Open the green trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"e517076b-2ed5-4da3-89d0-4a5b2e1d84fa","predictions":{"RoboJev-27B":0.7917237972510875,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.6527952390029181,"TypeSafe Jev 1.14":0.79,"Perplexity Decider":0.5815593232145108,"Liquid D1":0.7981867729389246,"Mercury Decide":0.7981867729389246,"Cloudflare Clef":0.7016,"cloudflare/clef-flash":0.7768,"cloudflare/clef-omni":0.4606,"liquid/d1-ultra":0.9379093666277238,"open/intern-decision-4b":0.767101934678807,"open/robojev-27b-v1@0.5":0.9145119816458417,"open/robojev-27b":null,"open/robojev-4b-v2":0.8267118019830628,"open/robojev-4b-v3@0.25":0.9626730680465698,"open/robojev-4b-v3@0.5":0.961715889902337,"open/robojev-4b-v3@0.75":0.9590959433649857,"open/robojev-4b-v3":0.9568029835538762,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.8606429718820504,"respan/span-02":0.95550966,"typesafe/jev-1.13":0.6,"JEV-27B-VL (10 frames)":0.716720627198951,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.016357421875}},{"suite":"unseen","id":"rbm-ood/usc_koch/e69006dd-9929-4778-9ac8-772778533dcf","task":"Separate the purple and orange cups","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"e69006dd-9929-4778-9ac8-772778533dcf","predictions":{"RoboJev-27B":0.9298270609745092,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.8940967838892754,"TypeSafe Jev 1.14":0.77,"Perplexity Decider":0.9099621849276227,"Liquid D1":0.9937100971412934,"Mercury Decide":0.9933071475773755,"Cloudflare Clef":0.8074,"cloudflare/clef-flash":0.7891,"cloudflare/clef-omni":0.1425,"liquid/d1-ultra":0.8360373935955678,"open/intern-decision-4b":0.767101934678807,"open/robojev-27b-v1@0.5":0.9761469133049848,"open/robojev-27b":null,"open/robojev-4b-v2":0.5774953711467454,"open/robojev-4b-v3@0.25":0.9525741338729858,"open/robojev-4b-v3@0.5":0.9328665051276483,"open/robojev-4b-v3@0.75":0.8489244915244398,"open/robojev-4b-v3":0.5939779701039213,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.8300962324130163,"respan/span-02":0.8787528,"typesafe/jev-1.13":0.89,"JEV-27B-VL (10 frames)":0.9015487248046213,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.08251953125}},{"suite":"unseen","id":"rbm-ood/usc_koch/ea21ecd7-794b-48a3-a79b-983ed6d562d9","task":"Separate the red and orange cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"ea21ecd7-794b-48a3-a79b-983ed6d562d9","predictions":{"RoboJev-27B":0.8194975928920728,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.8621068923576506,"TypeSafe Jev 1.14":0.54,"Perplexity Decider":0.8113726178574593,"Liquid D1":0.9626731142622272,"Mercury Decide":0.9796676485124378,"Cloudflare Clef":0.6548,"cloudflare/clef-flash":0.7442,"cloudflare/clef-omni":0.2949,"liquid/d1-ultra":0.8613434793059986,"open/intern-decision-4b":0.7557061813028185,"open/robojev-27b-v1@0.5":0.8690462430868919,"open/robojev-27b":null,"open/robojev-4b-v2":0.7772998717278379,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.9368711827232762,"open/robojev-4b-v3@0.75":0.8832743426844196,"open/robojev-4b-v3":0.828649621504827,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.6575210318930037,"respan/span-02":0.6184636,"typesafe/jev-1.13":0.57,"JEV-27B-VL (10 frames)":0.8169611491793888,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.064453125}},{"suite":"unseen","id":"rbm-ood/usc_koch/eb59f095-c125-473d-b305-22462d7b66cb","task":"Separate the purple and red cups","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"eb59f095-c125-473d-b305-22462d7b66cb","predictions":{"RoboJev-27B":0.822113067154505,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.9011716125104581,"TypeSafe Jev 1.14":0.85,"Perplexity Decider":0.8666566556267647,"Liquid D1":0.9830850867332734,"Mercury Decide":0.9820137927685547,"Cloudflare Clef":0.8049,"cloudflare/clef-flash":0.8029,"cloudflare/clef-omni":0.3336,"liquid/d1-ultra":0.5613944930420245,"open/intern-decision-4b":0.8184242551251981,"open/robojev-27b-v1@0.5":0.9312663555419055,"open/robojev-27b":null,"open/robojev-4b-v2":0.9272127908057297,"open/robojev-4b-v3@0.25":0.9669140577316284,"open/robojev-4b-v3@0.5":0.9286271325815819,"open/robojev-4b-v3@0.75":0.756014627783845,"open/robojev-4b-v3":0.3303678724294036,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9432205328045495,"respan/span-02":0.30326813,"typesafe/jev-1.13":0.83,"JEV-27B-VL (10 frames)":0.8751839075763548,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.007354736328125}},{"suite":"unseen","id":"rbm-ood/usc_koch/f30457a0-5cb7-4412-b873-e63d93de6ad1","task":"Throw the orange cup away in the red trash can","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"f30457a0-5cb7-4412-b873-e63d93de6ad1","predictions":{"RoboJev-27B":0.6369831137508928,"GPT-6 Astra":0.18,"GPT-6.1 Sol":0.38,"Claude Opus 5.5":0.25,"Claude Sonnet 5.5":0.35,"JEV-27B-VL":0.8143605393978726,"TypeSafe Jev 1.14":0.49,"Perplexity Decider":0.7519766462345742,"Liquid D1":0.9669140187510509,"Mercury Decide":0.8807970889295664,"Cloudflare Clef":0.7246,"cloudflare/clef-flash":0.7263,"cloudflare/clef-omni":0.3627,"liquid/d1-ultra":0.4753376834348995,"open/intern-decision-4b":0.844739173437523,"open/robojev-27b-v1@0.5":0.9399528355294168,"open/robojev-27b":null,"open/robojev-4b-v2":0.7185943895092446,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.7152565465994749,"open/robojev-4b-v3@0.75":0.2666072781234324,"open/robojev-4b-v3":0.24208096504423623,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.7600100768225696,"respan/span-02":0.7187449,"typesafe/jev-1.13":0.55,"JEV-27B-VL (10 frames)":0.7517228019339033,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.04541015625}},{"suite":"unseen","id":"rbm-ood/usc_koch/f3e2bbe5-64df-4ccd-9251-8bdb0bf8e195","task":"Throw the black marker away in the blue trash can","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"f3e2bbe5-64df-4ccd-9251-8bdb0bf8e195","predictions":{"RoboJev-27B":0.8159761366439999,"GPT-6 Astra":0.86,"GPT-6.1 Sol":0.86,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.7768718518621963,"TypeSafe Jev 1.14":0.67,"Perplexity Decider":0.8878618580722413,"Liquid D1":0.8740772286044095,"Mercury Decide":0.9669140250674247,"Cloudflare Clef":0.3458,"cloudflare/clef-flash":0.4551,"cloudflare/clef-omni":0.1025,"liquid/d1-ultra":0.7568318468916103,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.9546354502873521,"open/robojev-27b":null,"open/robojev-4b-v2":0.002751490629587489,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.12199371684192196,"open/robojev-4b-v3@0.75":0.1295704729794557,"open/robojev-4b-v3":0.21343419258585974,"openai/gpt-6-luna-decisions":0.12,"perplexity/pplx-decider-flash-v1.2":0.19796527802935743,"respan/span-02":0.61053294,"typesafe/jev-1.13":0.59,"JEV-27B-VL (10 frames)":0.7007885767981904,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.004058837890625}},{"suite":"unseen","id":"rbm-ood/usc_koch/f83e7747-d87d-450f-9bda-c943c0a40717","task":"Open the green trash bin","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"f83e7747-d87d-450f-9bda-c943c0a40717","predictions":{"RoboJev-27B":0.7913454911970428,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.62,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.7127197100322601,"TypeSafe Jev 1.14":0.35,"Perplexity Decider":0.43876945817713175,"Liquid D1":0.7772998508568416,"Mercury Decide":0.8933093975331751,"Cloudflare Clef":0.6414,"cloudflare/clef-flash":0.4493,"cloudflare/clef-omni":0.4759,"liquid/d1-ultra":0.8291578048646843,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.9110531393764147,"open/robojev-27b":null,"open/robojev-4b-v2":0.0893637337766288,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.04078132817181798,"open/robojev-4b-v3@0.75":0.04330410454906981,"open/robojev-4b-v3":0.09724120311457327,"openai/gpt-6-luna-decisions":0.99,"perplexity/pplx-decider-flash-v1.2":0.43226044227120947,"respan/span-02":0.96413445,"typesafe/jev-1.13":0.4,"JEV-27B-VL (10 frames)":0.7223922264980966,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.031982421875}},{"suite":"unseen","id":"rbm-ood/usc_koch/fbead96c-1271-4b3c-b77d-f48a21b2a0bd","task":"Open the red trash bin","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_koch","episode":"fbead96c-1271-4b3c-b77d-f48a21b2a0bd","predictions":{"RoboJev-27B":0.07368274033796063,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.06459043597655864,"TypeSafe Jev 1.14":0.33,"Perplexity Decider":0.15011786660158533,"Liquid D1":0.2814056014026228,"Mercury Decide":0.053403330929736405,"Cloudflare Clef":0.4176,"cloudflare/clef-flash":0.2582,"cloudflare/clef-omni":0.1409,"liquid/d1-ultra":0.2914061502706864,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.0090445037618538,"open/robojev-27b":null,"open/robojev-4b-v2":0.012991835391526811,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.11512034374911738,"open/robojev-4b-v3@0.75":0.1167256573155804,"open/robojev-4b-v3":0.10211768392406631,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.16738175100780733,"respan/span-02":0.12548068,"typesafe/jev-1.13":0.21,"JEV-27B-VL (10 frames)":0.25431439707417947,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00537109375}},{"suite":"unseen","id":"rbm-ood/usc_trossen/043753c3-f59f-494f-944f-52fdd604f7b2","task":"Unzip the pencil case","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"043753c3-f59f-494f-944f-52fdd604f7b2","predictions":{"RoboJev-27B":0.6952828504373388,"GPT-6 Astra":0.15,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.35764336731027874,"TypeSafe Jev 1.14":0.4,"Perplexity Decider":0.4747417582266794,"Liquid D1":0.679178699175393,"Mercury Decide":0.5621765008857981,"Cloudflare Clef":0.4005,"cloudflare/clef-flash":0.3211,"cloudflare/clef-omni":0.3551,"liquid/d1-ultra":0.30170334764715173,"open/intern-decision-4b":0.3201997500236374,"open/robojev-27b-v1@0.5":0.696188583951164,"open/robojev-27b":null,"open/robojev-4b-v2":0.154932285758515,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.07585817666120565,"open/robojev-4b-v3@0.75":0.05133579603952293,"open/robojev-4b-v3":0.025548296110078653,"openai/gpt-6-luna-decisions":0.82,"perplexity/pplx-decider-flash-v1.2":0.39570027219294884,"respan/span-02":0.86623204,"typesafe/jev-1.13":0.39,"JEV-27B-VL (10 frames)":0.6119529504383938,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000881195068359375}},{"suite":"unseen","id":"rbm-ood/usc_trossen/08dec425-2969-4989-9c40-8468babfad1d","task":"Remove the lid from the pot","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"08dec425-2969-4989-9c40-8468babfad1d","predictions":{"RoboJev-27B":0.3298754935511073,"GPT-6 Astra":0.86,"GPT-6.1 Sol":0.87,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.22572726966538817,"TypeSafe Jev 1.14":0.28,"Perplexity Decider":0.20248176692300746,"Liquid D1":0.32082130082460697,"Mercury Decide":0.020332355160653567,"Cloudflare Clef":0.3521,"cloudflare/clef-flash":0.2255,"cloudflare/clef-omni":0.1681,"liquid/d1-ultra":0.3448530892810048,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.21276266104012181,"open/robojev-27b":null,"open/robojev-4b-v2":0.021056067200550033,"open/robojev-4b-v3@0.25":0.10669060051441193,"open/robojev-4b-v3@0.5":0.059347834814291,"open/robojev-4b-v3@0.75":0.030697934885315165,"open/robojev-4b-v3":0.03326028532667912,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.10030196699102739,"respan/span-02":0.6215252,"typesafe/jev-1.13":0.51,"JEV-27B-VL (10 frames)":0.5378623553884057,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0005035400390625}},{"suite":"unseen","id":"rbm-ood/usc_trossen/1372e792-8b26-41a5-aa02-01528fc941a2","task":"Unzip the pencil case","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"1372e792-8b26-41a5-aa02-01528fc941a2","predictions":{"RoboJev-27B":0.3647698978959099,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.28560950676205016,"TypeSafe Jev 1.14":0.42,"Perplexity Decider":0.274821525783469,"Liquid D1":0.6513548646660542,"Mercury Decide":0.3486451217982255,"Cloudflare Clef":0.4253,"cloudflare/clef-flash":0.492,"cloudflare/clef-omni":0.4984,"liquid/d1-ultra":0.35608980418221525,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.45483099008966327,"open/robojev-27b":null,"open/robojev-4b-v2":0.04032423126830159,"open/robojev-4b-v3@0.25":0.22270014882087708,"open/robojev-4b-v3@0.5":0.1447586588133107,"open/robojev-4b-v3@0.75":0.1167256573155804,"open/robojev-4b-v3":0.10211768392406631,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.4175822479233496,"respan/span-02":0.8335136,"typesafe/jev-1.13":0.49,"JEV-27B-VL (10 frames)":0.21277991180518432,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00093841552734375}},{"suite":"unseen","id":"rbm-ood/usc_trossen/2617cb6b-180f-4ffb-b9e7-d87dcf914de0","task":"Uncap the red pen","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"2617cb6b-180f-4ffb-b9e7-d87dcf914de0","predictions":{"RoboJev-27B":0.027551861951231743,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.019006403723931146,"TypeSafe Jev 1.14":0.11,"Perplexity Decider":0.03655818759730866,"Liquid D1":0.14033624589467186,"Mercury Decide":0.005911068697539245,"Cloudflare Clef":0.2113,"cloudflare/clef-flash":0.2669,"cloudflare/clef-omni":0.2427,"liquid/d1-ultra":0.13865651366581622,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.0023740700767320446,"open/robojev-27b":null,"open/robojev-4b-v2":0.02618406111961536,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.01203420913122135,"open/robojev-4b-v3@0.75":0.008476838215708002,"open/robojev-4b-v3":0.007064018099624773,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.09471596447519069,"respan/span-02":0.16943595,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.02281802539430444,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0013275146484375}},{"suite":"unseen","id":"rbm-ood/usc_trossen/4798c411-caa3-405e-9afa-132d0a2617f1","task":"Open the red drawer","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"4798c411-caa3-405e-9afa-132d0a2617f1","predictions":{"RoboJev-27B":0.01479808540709052,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.007041033495305617,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.024399492167147978,"Liquid D1":0.30735800417608683,"Mercury Decide":0.003593602758163229,"Cloudflare Clef":0.2647,"cloudflare/clef-flash":0.3798,"cloudflare/clef-omni":0.3023,"liquid/d1-ultra":0.10691173403166276,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.00100584790449806,"open/robojev-27b":null,"open/robojev-4b-v2":0.04392481517503748,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.017755273617510888,"open/robojev-4b-v3@0.75":0.01011736424150334,"open/robojev-4b-v3":0.009249319533522623,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.23284104895436938,"respan/span-02":0.25548947,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.023771805669250926,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000518798828125}},{"suite":"unseen","id":"rbm-ood/usc_trossen/6eeb8f4c-2929-4b6f-a85a-2038b6302784","task":"Open the red drawer","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"6eeb8f4c-2929-4b6f-a85a-2038b6302784","predictions":{"RoboJev-27B":0.9254981929647342,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.9782186145935863,"TypeSafe Jev 1.14":0.53,"Perplexity Decider":0.9605934329659703,"Liquid D1":0.983085085370437,"Mercury Decide":0.9964063976403424,"Cloudflare Clef":0.8669,"cloudflare/clef-flash":0.5455,"cloudflare/clef-omni":0.5382,"liquid/d1-ultra":0.6092789380286551,"open/intern-decision-4b":0.4686721718608801,"open/robojev-27b-v1@0.5":0.9886704797794227,"open/robojev-27b":null,"open/robojev-4b-v2":0.9176406811912098,"open/robojev-4b-v3@0.25":0.977022647857666,"open/robojev-4b-v3@0.5":0.9784541229757918,"open/robojev-4b-v3@0.75":0.9674805555803846,"open/robojev-4b-v3":0.9495393243071166,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.7669895791520057,"respan/span-02":0.94743246,"typesafe/jev-1.13":0.6,"JEV-27B-VL (10 frames)":0.8988628845711761,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.04150390625}},{"suite":"unseen","id":"rbm-ood/usc_trossen/8bc4e6db-3dfb-4d9a-88d5-a7790ea4a9e7","task":"Stir the pot","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"8bc4e6db-3dfb-4d9a-88d5-a7790ea4a9e7","predictions":{"RoboJev-27B":0.6396303845542153,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.87,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.4519506389078053,"TypeSafe Jev 1.14":0.58,"Perplexity Decider":0.29222374337636875,"Liquid D1":0.8354835330070839,"Mercury Decide":0.3775406617944891,"Cloudflare Clef":0.5521,"cloudflare/clef-flash":0.6071,"cloudflare/clef-omni":0.6023,"liquid/d1-ultra":0.620965177756194,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.5301141079685032,"open/robojev-27b":null,"open/robojev-4b-v2":0.8267118019830628,"open/robojev-4b-v3@0.25":0.8354835510253906,"open/robojev-4b-v3@0.5":0.7992444628236429,"open/robojev-4b-v3@0.75":0.4851234373721735,"open/robojev-4b-v3":0.3929848669324905,"openai/gpt-6-luna-decisions":0.12,"perplexity/pplx-decider-flash-v1.2":0.5888990587149872,"respan/span-02":0.8701158,"typesafe/jev-1.13":0.42,"JEV-27B-VL (10 frames)":0.2949744672796764,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.004913330078125}},{"suite":"unseen","id":"rbm-ood/usc_trossen/8d2311da-1e57-4117-b6fe-52332558902b","task":"Remove the lid from the pot","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"8d2311da-1e57-4117-b6fe-52332558902b","predictions":{"RoboJev-27B":0.014733079795211778,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.019295759634028357,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.03411670073415139,"Liquid D1":0.30735801686526387,"Mercury Decide":0.004609572012719031,"Cloudflare Clef":0.1525,"cloudflare/clef-flash":0.3277,"cloudflare/clef-omni":0.1061,"liquid/d1-ultra":0.16396260801777635,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.0022357726212046776,"open/robojev-27b":null,"open/robojev-4b-v2":0.028559627850600573,"open/robojev-4b-v3@0.25":0.11920291930437088,"open/robojev-4b-v3@0.5":0.01203420913122135,"open/robojev-4b-v3@0.75":0.007990902377034759,"open/robojev-4b-v3":0.007868747659394765,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.27818842395208004,"respan/span-02":0.6906575,"typesafe/jev-1.13":0.12,"JEV-27B-VL (10 frames)":0.020500683209816697,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0006866455078125}},{"suite":"unseen","id":"rbm-ood/usc_trossen/92d0676b-eb5c-4f95-961c-d7320be8c3ca","task":"Stir the pot","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"92d0676b-eb5c-4f95-961c-d7320be8c3ca","predictions":{"RoboJev-27B":0.7564884921943877,"GPT-6 Astra":0.81,"GPT-6.1 Sol":0.87,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.3147157999474331,"TypeSafe Jev 1.14":0.47,"Perplexity Decider":0.3936306026475636,"Liquid D1":0.7057850154599563,"Mercury Decide":0.2689414096510108,"Cloudflare Clef":0.3537,"cloudflare/clef-flash":0.3636,"cloudflare/clef-omni":0.4728,"liquid/d1-ultra":0.4144612690663902,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.2893732601602662,"open/robojev-27b":null,"open/robojev-4b-v2":0.16086775395337108,"open/robojev-4b-v3@0.25":0.7981867790222168,"open/robojev-4b-v3@0.5":0.7772998746436928,"open/robojev-4b-v3@0.75":0.4407557950301173,"open/robojev-4b-v3":0.3067798159797107,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.5749080651137305,"respan/span-02":0.72449964,"typesafe/jev-1.13":0.2,"JEV-27B-VL (10 frames)":0.3629898709132427,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00421142578125}},{"suite":"unseen","id":"rbm-ood/usc_trossen/ababf79a-774d-4e0e-930f-24c7e0cf8a51","task":"Stir the pot","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"ababf79a-774d-4e0e-930f-24c7e0cf8a51","predictions":{"RoboJev-27B":0.28617156548669676,"GPT-6 Astra":0.89,"GPT-6.1 Sol":0.87,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.30158075120343686,"TypeSafe Jev 1.14":0.45,"Perplexity Decider":0.28666705580354557,"Liquid D1":0.679178699175393,"Mercury Decide":0.04742586846527418,"Cloudflare Clef":0.5447,"cloudflare/clef-flash":0.4863,"cloudflare/clef-omni":0.4231,"liquid/d1-ultra":0.24316814877634804,"open/intern-decision-4b":0.39193998888916504,"open/robojev-27b-v1@0.5":0.058142721924342555,"open/robojev-27b":null,"open/robojev-4b-v2":0.14359896340218653,"open/robojev-4b-v3@0.25":0.3775406777858734,"open/robojev-4b-v3@0.5":0.3122816956327956,"open/robojev-4b-v3@0.75":0.27840626377504696,"open/robojev-4b-v3":0.20445237038006636,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.6384241504138387,"respan/span-02":0.7426157,"typesafe/jev-1.13":0.25,"JEV-27B-VL (10 frames)":0.20524481771193046,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0021209716796875}},{"suite":"unseen","id":"rbm-ood/usc_trossen/bf3d54f4-482e-4f3a-a20f-bbcdc8c699e7","task":"Unzip the pencil case","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"bf3d54f4-482e-4f3a-a20f-bbcdc8c699e7","predictions":{"RoboJev-27B":0.21193190662114306,"GPT-6 Astra":0.89,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.35,"JEV-27B-VL":0.24942928575838944,"TypeSafe Jev 1.14":0.34,"Perplexity Decider":0.26990242903249,"Liquid D1":0.7772998663336157,"Mercury Decide":0.06754668738548215,"Cloudflare Clef":0.3585,"cloudflare/clef-flash":0.4261,"cloudflare/clef-omni":0.4295,"liquid/d1-ultra":0.3448530892810048,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.14837298445300612,"open/robojev-27b":null,"open/robojev-4b-v2":0.03700737584165394,"open/robojev-4b-v3@0.25":0.2689414322376251,"open/robojev-4b-v3@0.5":0.12199371684192196,"open/robojev-4b-v3@0.75":0.06076252040232631,"open/robojev-4b-v3":0.028398519832920938,"openai/gpt-6-luna-decisions":0.6,"perplexity/pplx-decider-flash-v1.2":0.5241929767759678,"respan/span-02":0.8415115,"typesafe/jev-1.13":0.4,"JEV-27B-VL (10 frames)":0.10028545204414625,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0007781982421875}},{"suite":"unseen","id":"rbm-ood/usc_trossen/bfad213d-ef98-41ea-9023-174e018287a0","task":"Open the bottle","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"bfad213d-ef98-41ea-9023-174e018287a0","predictions":{"RoboJev-27B":0.08414043190938432,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.028316907005256044,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.04046496513388702,"Liquid D1":0.11920292202211755,"Mercury Decide":0.005220124866560973,"Cloudflare Clef":0.1904,"cloudflare/clef-flash":0.2612,"cloudflare/clef-omni":0.1769,"liquid/d1-ultra":0.10691173515542979,"open/intern-decision-4b":0.21123545993246395,"open/robojev-27b-v1@0.5":0.0035543000715119364,"open/robojev-27b":null,"open/robojev-4b-v2":0.03251944279343901,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.04625107524610428,"open/robojev-4b-v3@0.75":0.02167836395087896,"open/robojev-4b-v3":0.020659669708358676,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.14089512844596397,"respan/span-02":0.06667142,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.0785345636087403,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0010986328125}},{"suite":"unseen","id":"rbm-ood/usc_trossen/c243382e-cb06-42fb-a1ce-ec787a7da218","task":"Open the bottle","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"c243382e-cb06-42fb-a1ce-ec787a7da218","predictions":{"RoboJev-27B":0.0429175522274381,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":0.016030672817931416,"TypeSafe Jev 1.14":0.3,"Perplexity Decider":0.044498593241987565,"Liquid D1":0.2568319970758679,"Mercury Decide":0.004609572320390132,"Cloudflare Clef":0.2455,"cloudflare/clef-flash":0.206,"cloudflare/clef-omni":0.3804,"liquid/d1-ultra":0.15730750212730107,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.0036466693105519973,"open/robojev-27b":null,"open/robojev-4b-v2":0.005604465165684275,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.1804712758005596,"open/robojev-4b-v3@0.75":0.20277377238617383,"open/robojev-4b-v3":0.48641638460333464,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.19205972498584448,"respan/span-02":0.13287345,"typesafe/jev-1.13":0.24,"JEV-27B-VL (10 frames)":0.017422854491461737,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00193023681640625}},{"suite":"unseen","id":"rbm-ood/usc_trossen/c8613f0d-474c-46ec-958d-f3bcfb132372","task":"Open the red drawer","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"c8613f0d-474c-46ec-958d-f3bcfb132372","predictions":{"RoboJev-27B":0.9803404680393267,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.95,"JEV-27B-VL":0.9872285140508074,"TypeSafe Jev 1.14":0.77,"Perplexity Decider":0.9747855422083558,"Liquid D1":0.9324533130837861,"Mercury Decide":0.9975273772223893,"Cloudflare Clef":0.9476,"cloudflare/clef-flash":0.8316,"cloudflare/clef-omni":0.7583,"liquid/d1-ultra":0.8491262276507164,"open/intern-decision-4b":0.6659927647326706,"open/robojev-27b-v1@0.5":0.9960400358373674,"open/robojev-27b":null,"open/robojev-4b-v2":0.9521691293545035,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.9784541229757918,"open/robojev-4b-v3@0.75":0.9566958954509301,"open/robojev-4b-v3":0.9348103782119872,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.7757951289433421,"respan/span-02":0.90685356,"typesafe/jev-1.13":0.82,"JEV-27B-VL (10 frames)":0.9669213536652631,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00445556640625}},{"suite":"unseen","id":"rbm-ood/usc_trossen/cc2a5e47-6f33-4763-9f7c-ece094b42225","task":"Open the bottle","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"cc2a5e47-6f33-4763-9f7c-ece094b42225","predictions":{"RoboJev-27B":0.03631195167246402,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.01425238999836144,"TypeSafe Jev 1.14":0.24,"Perplexity Decider":0.07125275720629885,"Liquid D1":0.0900929890757869,"Mercury Decide":0.0033766122156323715,"Cloudflare Clef":0.2426,"cloudflare/clef-flash":0.184,"cloudflare/clef-omni":0.1687,"liquid/d1-ultra":0.17794899285306523,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.004291628832401431,"open/robojev-27b":null,"open/robojev-4b-v2":0.009969411693719354,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.07137286741841814,"open/robojev-4b-v3@0.75":0.0717892678456694,"open/robojev-4b-v3":0.050460675692883365,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.2115621804130831,"respan/span-02":0.13527781,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.017927757339753405,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00113677978515625}},{"suite":"unseen","id":"rbm-ood/usc_trossen/cd11463a-39eb-45ce-9bb9-0b9f76e4f63d","task":"Unzip the pencil case","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"cd11463a-39eb-45ce-9bb9-0b9f76e4f63d","predictions":{"RoboJev-27B":0.7123926161655327,"GPT-6 Astra":0.92,"GPT-6.1 Sol":0.91,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.377333288902431,"TypeSafe Jev 1.14":0.44,"Perplexity Decider":0.33749432282503294,"Liquid D1":0.8519528057272543,"Mercury Decide":0.24508500761839525,"Cloudflare Clef":0.5524,"cloudflare/clef-flash":0.5685,"cloudflare/clef-omni":0.4103,"liquid/d1-ultra":0.3448530892810048,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.4373276025577157,"open/robojev-27b":null,"open/robojev-4b-v2":0.04583824899717374,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.059347834814291,"open/robojev-4b-v3@0.75":0.027346787282274982,"open/robojev-4b-v3":0.01421514020851167,"openai/gpt-6-luna-decisions":0.92,"perplexity/pplx-decider-flash-v1.2":0.4488711830542307,"respan/span-02":0.8253276,"typesafe/jev-1.13":0.37,"JEV-27B-VL (10 frames)":0.44022227904695455,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00116729736328125}},{"suite":"unseen","id":"rbm-ood/usc_trossen/da5b17da-f053-47f0-81d4-275cd1bd668b","task":"Open the bottle","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"da5b17da-f053-47f0-81d4-275cd1bd668b","predictions":{"RoboJev-27B":0.554668017350793,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.12,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.09022323717662534,"TypeSafe Jev 1.14":0.32,"Perplexity Decider":0.17978966827587858,"Liquid D1":0.3923368301671084,"Mercury Decide":0.0850990438468576,"Cloudflare Clef":0.1921,"cloudflare/clef-flash":0.213,"cloudflare/clef-omni":0.1184,"liquid/d1-ultra":0.1708422134745657,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.11818450367572549,"open/robojev-27b":null,"open/robojev-4b-v2":0.10927050321483402,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.6734177885000919,"open/robojev-4b-v3@0.75":0.6445661085951192,"open/robojev-4b-v3":0.3067798159797107,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.17997200196262203,"respan/span-02":0.07683573,"typesafe/jev-1.13":0.24,"JEV-27B-VL (10 frames)":0.2650495773072323,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0007781982421875}},{"suite":"unseen","id":"rbm-ood/usc_trossen/e8b107bc-985d-4093-85a9-fa3e4a88eeaa","task":"Unzip the pencil case","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"e8b107bc-985d-4093-85a9-fa3e4a88eeaa","predictions":{"RoboJev-27B":0.5174535235161548,"GPT-6 Astra":0.78,"GPT-6.1 Sol":0.18,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.19506154233690787,"TypeSafe Jev 1.14":0.33,"Perplexity Decider":0.19979606741664802,"Liquid D1":0.798186768138228,"Mercury Decide":0.09534945847239201,"Cloudflare Clef":0.4688,"cloudflare/clef-flash":0.3485,"cloudflare/clef-omni":0.576,"liquid/d1-ultra":0.333787150806788,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.08966772740551326,"open/robojev-27b":null,"open/robojev-4b-v2":0.06424971190493048,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.04078132817181798,"open/robojev-4b-v3@0.75":0.02580728323952834,"open/robojev-4b-v3":0.017606235547797083,"openai/gpt-6-luna-decisions":0.18,"perplexity/pplx-decider-flash-v1.2":0.4065814586830715,"respan/span-02":0.7002989,"typesafe/jev-1.13":0.36,"JEV-27B-VL (10 frames)":0.3045562576010709,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0006256103515625}},{"suite":"unseen","id":"rbm-ood/usc_trossen/ec723696-61c2-478a-a21f-0c4bf7f9a0d7","task":"Open the bottle","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"ec723696-61c2-478a-a21f-0c4bf7f9a0d7","predictions":{"RoboJev-27B":0.02362788350812091,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.0015888231753517308,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.03472541781011342,"Liquid D1":0.07585817688736327,"Mercury Decide":0.0010987308337418616,"Cloudflare Clef":0.1453,"cloudflare/clef-flash":0.2064,"cloudflare/clef-omni":0.1127,"liquid/d1-ultra":0.12189696907519396,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.0012738203933865895,"open/robojev-27b":null,"open/robojev-4b-v2":0.011895327908303815,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.04924136119799765,"open/robojev-4b-v3@0.75":0.057452972917902974,"open/robojev-4b-v3":0.09724120311457327,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.1551077767817539,"respan/span-02":0.19021377,"typesafe/jev-1.13":0.15,"JEV-27B-VL (10 frames)":0.016213952460254095,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0025482177734375}},{"suite":"unseen","id":"rbm-ood/usc_trossen/fab793f7-2b04-4425-8af9-9e50ea6e0079","task":"Open the red drawer","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"fab793f7-2b04-4425-8af9-9e50ea6e0079","predictions":{"RoboJev-27B":0.9354813465424932,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.969242282453232,"TypeSafe Jev 1.14":0.39,"Perplexity Decider":0.9374064235075806,"Liquid D1":0.9465966671870767,"Mercury Decide":0.9947798735471515,"Cloudflare Clef":0.8436,"cloudflare/clef-flash":0.7747,"cloudflare/clef-omni":0.4208,"liquid/d1-ultra":0.6092789156141315,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.9929839623039155,"open/robojev-27b":null,"open/robojev-4b-v2":0.8720986012807731,"open/robojev-4b-v3@0.25":0.9324532747268677,"open/robojev-4b-v3@0.5":0.975498409742533,"open/robojev-4b-v3@0.75":0.9566958954509301,"open/robojev-4b-v3":0.9348103782119872,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.8707228123910047,"respan/span-02":0.9676617,"typesafe/jev-1.13":0.71,"JEV-27B-VL (10 frames)":0.9377629916180688,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01361083984375}},{"suite":"unseen","id":"rbm-ood/usc_trossen/fcdd7b74-542e-455f-aca8-f6bd110144a8","task":"Open the red drawer","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_trossen","episode":"fcdd7b74-542e-455f-aca8-f6bd110144a8","predictions":{"RoboJev-27B":0.03255821869106219,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.08,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.02895966670144333,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.06339835893043083,"Liquid D1":0.2942149597859341,"Mercury Decide":0.01798621348232278,"Cloudflare Clef":0.2509,"cloudflare/clef-flash":0.4363,"cloudflare/clef-omni":0.18,"liquid/d1-ultra":0.12728027447240892,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.005454741452961822,"open/robojev-27b":null,"open/robojev-4b-v2":0.1381957315129781,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.10858632498619036,"open/robojev-4b-v3@0.75":0.0458382546620802,"open/robojev-4b-v3":0.06195489972932116,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.2793517286770535,"respan/span-02":0.8411051,"typesafe/jev-1.13":0.27,"JEV-27B-VL (10 frames)":0.04570718402853547,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.000457763671875}},{"suite":"unseen","id":"rbm-ood/usc_xarm/0947d5d3-1346-472e-9640-4e5c4f9141b7","task":"Put the eggplant in the black bowl","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"0947d5d3-1346-472e-9640-4e5c4f9141b7","predictions":{"RoboJev-27B":0.009180820953806207,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.6999399381302502,"TypeSafe Jev 1.14":0.31,"Perplexity Decider":0.21482619063883593,"Liquid D1":0.9669140187510509,"Mercury Decide":0.6513548646660542,"Cloudflare Clef":0.4399,"cloudflare/clef-flash":0.1526,"cloudflare/clef-omni":0.3277,"liquid/d1-ultra":0.5613944930420245,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.49925084468158165,"open/robojev-27b":null,"open/robojev-4b-v2":0.021056067200550033,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.017755273617510888,"open/robojev-4b-v3@0.75":0.0143976132495814,"open/robojev-4b-v3":0.009760866998496955,"openai/gpt-6-luna-decisions":0.92,"perplexity/pplx-decider-flash-v1.2":0.16491304538388735,"respan/span-02":0.12665305,"typesafe/jev-1.13":0.34,"JEV-27B-VL (10 frames)":6.962769759711441e-05,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2158203125}},{"suite":"unseen","id":"rbm-ood/usc_xarm/0bd8cd2f-85b2-4143-992a-2e185c502103","task":"Put blue cup in sink","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"0bd8cd2f-85b2-4143-992a-2e185c502103","predictions":{"RoboJev-27B":0.0025557359849796954,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.0001640235434569639,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.017252613949273913,"Liquid D1":0.03963883626471278,"Mercury Decide":0.0009110510740258997,"Cloudflare Clef":0.1284,"cloudflare/clef-flash":0.174,"cloudflare/clef-omni":0.0967,"liquid/d1-ultra":0.044761571979980826,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.00017930071272166713,"open/robojev-27b":null,"open/robojev-4b-v2":0.009125637690971435,"open/robojev-4b-v3@0.25":0.014063626527786255,"open/robojev-4b-v3@0.5":0.004825770646864498,"open/robojev-4b-v3@0.75":0.005282311488788821,"open/robojev-4b-v3":0.006341061537493235,"openai/gpt-6-luna-decisions":0.07,"perplexity/pplx-decider-flash-v1.2":0.1082772740496784,"respan/span-02":0.047805414,"typesafe/jev-1.13":0.07,"JEV-27B-VL (10 frames)":0.0007034444167192672,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006683349609375}},{"suite":"unseen","id":"rbm-ood/usc_xarm/312f4b8a-6633-43bd-9094-e6ec964d609a","task":"Put the eggplant in the black bowl","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"312f4b8a-6633-43bd-9094-e6ec964d609a","predictions":{"RoboJev-27B":0.9631693129475078,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.92,"JEV-27B-VL":0.4538591167627615,"TypeSafe Jev 1.14":0.74,"Perplexity Decider":0.3931638343085899,"Liquid D1":0.9859363709422372,"Mercury Decide":0.04742586796038571,"Cloudflare Clef":0.726,"cloudflare/clef-flash":0.4842,"cloudflare/clef-omni":0.3211,"liquid/d1-ultra":0.8781030208465609,"open/intern-decision-4b":0.767101934678807,"open/robojev-27b-v1@0.5":0.2719641753024809,"open/robojev-27b":null,"open/robojev-4b-v2":0.14917689162532846,"open/robojev-4b-v3@0.25":0.9626730680465698,"open/robojev-4b-v3@0.5":0.9640659266906685,"open/robojev-4b-v3@0.75":0.9392374795976737,"open/robojev-4b-v3":0.9314191245597471,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.73075902978437,"respan/span-02":0.93149513,"typesafe/jev-1.13":0.82,"JEV-27B-VL (10 frames)":0.9506775206879788,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.8515625}},{"suite":"unseen","id":"rbm-ood/usc_xarm/4f6262d5-427f-4fb1-9e88-0bf7c319e434","task":"Close the drawer","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"4f6262d5-427f-4fb1-9e88-0bf7c319e434","predictions":{"RoboJev-27B":0.6194645299071706,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.7251689188957724,"TypeSafe Jev 1.14":0.66,"Perplexity Decider":0.715480881514337,"Liquid D1":0.8807970842359877,"Mercury Decide":0.9626731119865551,"Cloudflare Clef":0.6301,"cloudflare/clef-flash":0.3196,"cloudflare/clef-omni":0.3882,"liquid/d1-ultra":0.6551469107189953,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.9574599653895595,"open/robojev-27b":null,"open/robojev-4b-v2":0.8135454576250908,"open/robojev-4b-v3@0.25":0.43782350420951843,"open/robojev-4b-v3@0.5":0.7284637291157656,"open/robojev-4b-v3@0.75":0.8330143287656493,"open/robojev-4b-v3":0.828649621504827,"openai/gpt-6-luna-decisions":0.45,"perplexity/pplx-decider-flash-v1.2":0.33687877933686594,"respan/span-02":0.49676853,"typesafe/jev-1.13":0.41,"JEV-27B-VL (10 frames)":0.5540864023110744,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.345703125}},{"suite":"unseen","id":"rbm-ood/usc_xarm/5244aaaa-04a0-4ccd-bbad-29b2e6c8023c","task":"Put the banana on the red plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"5244aaaa-04a0-4ccd-bbad-29b2e6c8023c","predictions":{"RoboJev-27B":0.012112223026808373,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.00039005500073370963,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.024186094666756107,"Liquid D1":0.5,"Mercury Decide":0.000552778687347605,"Cloudflare Clef":0.1011,"cloudflare/clef-flash":0.4714,"cloudflare/clef-omni":0.3826,"liquid/d1-ultra":0.07129505962525462,"open/intern-decision-4b":0.5624106420506467,"open/robojev-27b-v1@0.5":0.00011762143779480481,"open/robojev-27b":null,"open/robojev-4b-v2":0.06698650224956176,"open/robojev-4b-v3@0.25":0.13296423852443695,"open/robojev-4b-v3@0.5":0.1368024864039654,"open/robojev-4b-v3@0.75":0.15886909401879357,"open/robojev-4b-v3":0.20445237038006636,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.09551378634517618,"respan/span-02":0.08011368,"typesafe/jev-1.13":0.12,"JEV-27B-VL (10 frames)":7.626978737531332e-05,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0113525390625}},{"suite":"unseen","id":"rbm-ood/usc_xarm/64e17159-9d91-4147-bfe6-fe19c037f1b6","task":"Stack the green shape on the red cylinder","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"64e17159-9d91-4147-bfe6-fe19c037f1b6","predictions":{"RoboJev-27B":0.00014163299932373223,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":3.2409690648138432e-06,"TypeSafe Jev 1.14":0.02,"Perplexity Decider":0.005467417830357831,"Liquid D1":0.0015011821227223277,"Mercury Decide":0.0004583129603648556,"Cloudflare Clef":0.0272,"cloudflare/clef-flash":0.1061,"cloudflare/clef-omni":0.0444,"liquid/d1-ultra":0.026503365483917223,"open/intern-decision-4b":0.1395062328236417,"open/robojev-27b-v1@0.5":7.357607969966506e-06,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016856305131264125,"open/robojev-4b-v3@0.25":0.01098694372922182,"open/robojev-4b-v3@0.5":0.004233320503182646,"open/robojev-4b-v3@0.75":0.0029197498822566025,"open/robojev-4b-v3":0.002667578431318334,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.03959533339866865,"respan/span-02":0.034872156,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":2.3963241201997254e-06,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00128173828125}},{"suite":"unseen","id":"rbm-ood/usc_xarm/70cb5268-c3e6-4e87-99a1-95aa4ffe2899","task":"Put the eggplant in the black bowl","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"70cb5268-c3e6-4e87-99a1-95aa4ffe2899","predictions":{"RoboJev-27B":0.8939200375698417,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.75,"JEV-27B-VL":0.7236312201939816,"TypeSafe Jev 1.14":0.8,"Perplexity Decider":0.8884681536758123,"Liquid D1":0.9783846692857063,"Mercury Decide":0.8519527982093668,"Cloudflare Clef":0.7156,"cloudflare/clef-flash":0.5823,"cloudflare/clef-omni":0.2337,"liquid/d1-ultra":0.6092789156141315,"open/intern-decision-4b":0.7439389554145914,"open/robojev-27b-v1@0.5":0.9183292722890779,"open/robojev-27b":null,"open/robojev-4b-v2":0.6811210474999878,"open/robojev-4b-v3@0.25":0.977022647857666,"open/robojev-4b-v3@0.5":0.9833564251170067,"open/robojev-4b-v3@0.75":0.9655548037210256,"open/robojev-4b-v3":0.944069345153315,"openai/gpt-6-luna-decisions":0.1,"perplexity/pplx-decider-flash-v1.2":0.8643681556616166,"respan/span-02":0.93220556,"typesafe/jev-1.13":0.77,"JEV-27B-VL (10 frames)":0.7795155378443652,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.380859375}},{"suite":"unseen","id":"rbm-ood/usc_xarm/71847ff7-3199-4794-bc44-373cc5315777","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"71847ff7-3199-4794-bc44-373cc5315777","predictions":{"RoboJev-27B":0.8310469827749044,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.7267013048825145,"TypeSafe Jev 1.14":0.5,"Perplexity Decider":0.6289110023504735,"Liquid D1":0.8933094145755219,"Mercury Decide":0.9046505447409665,"Cloudflare Clef":0.3644,"cloudflare/clef-flash":0.4876,"cloudflare/clef-omni":0.3255,"liquid/d1-ultra":0.7745383798334267,"open/intern-decision-4b":0.6798002499763626,"open/robojev-27b-v1@0.5":0.927710808640511,"open/robojev-27b":null,"open/robojev-4b-v2":0.890729496785166,"open/robojev-4b-v3@0.25":0.970687747001648,"open/robojev-4b-v3@0.5":0.9640659266906685,"open/robojev-4b-v3@0.75":0.9241418132536457,"open/robojev-4b-v3":0.8761560328980749,"openai/gpt-6-luna-decisions":0.69,"perplexity/pplx-decider-flash-v1.2":0.896646472806966,"respan/span-02":0.18295966,"typesafe/jev-1.13":0.72,"JEV-27B-VL (10 frames)":0.6782055759513638,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.88671875}},{"suite":"unseen","id":"rbm-ood/usc_xarm/73b0fb7d-dc98-4a97-a39e-fe99acac7b2c","task":"Fold the towel in half","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"73b0fb7d-dc98-4a97-a39e-fe99acac7b2c","predictions":{"RoboJev-27B":0.5238275706826467,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.12,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":0.4011313775656054,"TypeSafe Jev 1.14":0.32,"Perplexity Decider":0.3340132248255201,"Liquid D1":0.8670357580842941,"Mercury Decide":0.4378234991142019,"Cloudflare Clef":0.3948,"cloudflare/clef-flash":0.4129,"cloudflare/clef-omni":0.3938,"liquid/d1-ultra":0.36748729255237933,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.6341562813138372,"open/robojev-27b":null,"open/robojev-4b-v2":0.8618042684870219,"open/robojev-4b-v3@0.25":0.29421496391296387,"open/robojev-4b-v3@0.5":0.4184967522309292,"open/robojev-4b-v3@0.75":0.777299857680221,"open/robojev-4b-v3":0.8042455501618967,"openai/gpt-6-luna-decisions":0.14,"perplexity/pplx-decider-flash-v1.2":0.2784274758440001,"respan/span-02":0.15531954,"typesafe/jev-1.13":0.22,"JEV-27B-VL (10 frames)":0.32924288679907315,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.3515625}},{"suite":"unseen","id":"rbm-ood/usc_xarm/84b5e7d9-7f36-4148-a635-196c90eb2b26","task":"Put blue cup in sink","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"84b5e7d9-7f36-4148-a635-196c90eb2b26","predictions":{"RoboJev-27B":0.9683281634836118,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.9650895771894044,"TypeSafe Jev 1.14":0.7,"Perplexity Decider":0.990283832434078,"Liquid D1":0.9875683480948912,"Mercury Decide":0.9968273170779886,"Cloudflare Clef":0.8879,"cloudflare/clef-flash":0.7136,"cloudflare/clef-omni":0.103,"liquid/d1-ultra":0.9287049411540257,"open/intern-decision-4b":0.91062577829021,"open/robojev-27b-v1@0.5":0.9924564827049045,"open/robojev-27b":null,"open/robojev-4b-v2":0.020155265089209666,"open/robojev-4b-v3@0.25":0.9875683188438416,"open/robojev-4b-v3@0.5":0.9907244334212516,"open/robojev-4b-v3@0.75":0.9924673890431385,"open/robojev-4b-v3":0.9916954182806045,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9663399793029068,"respan/span-02":0.95011306,"typesafe/jev-1.13":0.89,"JEV-27B-VL (10 frames)":0.9617590006817497,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.8046875}},{"suite":"unseen","id":"rbm-ood/usc_xarm/887bb1d0-ec5a-4f9d-844f-56f95a787790","task":"Fold the towel in half","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"887bb1d0-ec5a-4f9d-844f-56f95a787790","predictions":{"RoboJev-27B":0.18617499990532352,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.08959301067624328,"TypeSafe Jev 1.14":0.2,"Perplexity Decider":0.06662298683454168,"Liquid D1":0.5,"Mercury Decide":0.037326888281170874,"Cloudflare Clef":0.163,"cloudflare/clef-flash":0.4079,"cloudflare/clef-omni":0.1962,"liquid/d1-ultra":0.22546161194543257,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.06861858939988046,"open/robojev-27b":null,"open/robojev-4b-v2":0.8330143331540432,"open/robojev-4b-v3@0.25":0.4073334336280823,"open/robojev-4b-v3@0.5":0.34121268247291503,"open/robojev-4b-v3@0.75":0.6580827429772586,"open/robojev-4b-v3":0.6451587915501215,"openai/gpt-6-luna-decisions":0.06,"perplexity/pplx-decider-flash-v1.2":0.3390037478053405,"respan/span-02":0.18737972,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.07713044071365814,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.3828125}},{"suite":"unseen","id":"rbm-ood/usc_xarm/8d1d7235-b515-47b8-b8e8-c8d913d85ab7","task":"Close the drawer","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"8d1d7235-b515-47b8-b8e8-c8d913d85ab7","predictions":{"RoboJev-27B":0.15934258170827104,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.25087406123808326,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.19052553410943776,"Liquid D1":0.6513548511303336,"Mercury Decide":0.11920290950590741,"Cloudflare Clef":0.3832,"cloudflare/clef-flash":0.268,"cloudflare/clef-omni":0.3938,"liquid/d1-ultra":0.22546160783486224,"open/intern-decision-4b":0.37709365395745764,"open/robojev-27b-v1@0.5":0.05801083460122638,"open/robojev-27b":null,"open/robojev-4b-v2":0.03700737584165394,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.03372324040197287,"open/robojev-4b-v3@0.75":0.013576917981093352,"open/robojev-4b-v3":0.008764341864947102,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.30785077937053756,"respan/span-02":0.13857833,"typesafe/jev-1.13":0.23,"JEV-27B-VL (10 frames)":0.16851811434744893,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.051025390625}},{"suite":"unseen","id":"rbm-ood/usc_xarm/8ddf2911-58ad-46ba-87cd-7710f2920fbf","task":"Close the drawer","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"8ddf2911-58ad-46ba-87cd-7710f2920fbf","predictions":{"RoboJev-27B":0.7098755618440876,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.6527952390029181,"TypeSafe Jev 1.14":0.69,"Perplexity Decider":0.7115094097558335,"Liquid D1":0.8933093989533708,"Mercury Decide":0.7772998560157665,"Cloudflare Clef":0.4854,"cloudflare/clef-flash":0.3029,"cloudflare/clef-omni":0.3127,"liquid/d1-ultra":0.8727197307569977,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.9756097402838777,"open/robojev-27b":null,"open/robojev-4b-v2":0.23052358465184783,"open/robojev-4b-v3@0.25":0.8670357465744019,"open/robojev-4b-v3@0.5":0.9442201868171092,"open/robojev-4b-v3@0.75":0.9392374795976737,"open/robojev-4b-v3":0.9241418172849298,"openai/gpt-6-luna-decisions":0.55,"perplexity/pplx-decider-flash-v1.2":0.3484812086074451,"respan/span-02":0.16474147,"typesafe/jev-1.13":0.32,"JEV-27B-VL (10 frames)":0.6731595990015296,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.435546875}},{"suite":"unseen","id":"rbm-ood/usc_xarm/96fbffd6-97ce-464c-a63e-75f96c745592","task":"Stack the green shape on the red cylinder","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"96fbffd6-97ce-464c-a63e-75f96c745592","predictions":{"RoboJev-27B":0.9208443518772416,"GPT-6 Astra":0.93,"GPT-6.1 Sol":0.89,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.8752757958122362,"TypeSafe Jev 1.14":0.72,"Perplexity Decider":0.9362664280462335,"Liquid D1":0.946596667563714,"Mercury Decide":0.9840936096002363,"Cloudflare Clef":0.8555,"cloudflare/clef-flash":0.7595,"cloudflare/clef-omni":0.5613,"liquid/d1-ultra":0.855341985101059,"open/intern-decision-4b":0.844739173437523,"open/robojev-27b-v1@0.5":0.9710000387687333,"open/robojev-27b":null,"open/robojev-4b-v2":0.8450677142414851,"open/robojev-4b-v3@0.25":0.957912266254425,"open/robojev-4b-v3@0.5":0.9328665051276483,"open/robojev-4b-v3@0.75":0.8704295270205443,"open/robojev-4b-v3":0.7374213456765728,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.6724552237779602,"respan/span-02":0.9108903,"typesafe/jev-1.13":0.66,"JEV-27B-VL (10 frames)":0.8576487807187515,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.734375}},{"suite":"unseen","id":"rbm-ood/usc_xarm/9f99930c-cbf8-46b0-882f-ff7b3fcc4e93","task":"Close the drawer","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"9f99930c-cbf8-46b0-882f-ff7b3fcc4e93","predictions":{"RoboJev-27B":0.3290191175537501,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.13511396586121902,"TypeSafe Jev 1.14":0.12,"Perplexity Decider":0.2586740362116864,"Liquid D1":0.7057850278370112,"Mercury Decide":0.04208773257151255,"Cloudflare Clef":0.3744,"cloudflare/clef-flash":0.3097,"cloudflare/clef-omni":0.381,"liquid/d1-ultra":0.1328653217582325,"open/intern-decision-4b":0.4686721718608801,"open/robojev-27b-v1@0.5":0.030120827774249317,"open/robojev-27b":null,"open/robojev-4b-v2":0.042087729958985645,"open/robojev-4b-v3@0.25":0.18242551386356354,"open/robojev-4b-v3@0.5":0.02612421708095358,"open/robojev-4b-v3@0.75":0.010731211960485985,"open/robojev-4b-v3":0.006692851401910932,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.27897731329403774,"respan/span-02":0.620024,"typesafe/jev-1.13":0.3,"JEV-27B-VL (10 frames)":0.24953332687820126,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.068359375}},{"suite":"unseen","id":"rbm-ood/usc_xarm/ae38a588-1a6e-433b-8317-fff8fbcee422","task":"Stack the green shape on the red cylinder","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"ae38a588-1a6e-433b-8317-fff8fbcee422","predictions":{"RoboJev-27B":0.8546018155752605,"GPT-6 Astra":0.85,"GPT-6.1 Sol":0.8,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.6457797739167208,"TypeSafe Jev 1.14":0.49,"Perplexity Decider":0.600949258198188,"Liquid D1":0.7772998714925403,"Mercury Decide":0.9324533130837861,"Cloudflare Clef":0.5706,"cloudflare/clef-flash":0.4206,"cloudflare/clef-omni":0.2925,"liquid/d1-ultra":0.5613945046340345,"open/intern-decision-4b":0.788764540067536,"open/robojev-27b-v1@0.5":0.8100406666147175,"open/robojev-27b":null,"open/robojev-4b-v2":0.04392481517503748,"open/robojev-4b-v3@0.25":0.6791787147521973,"open/robojev-4b-v3@0.5":0.19040689770918212,"open/robojev-4b-v3@0.75":0.02167836395087896,"open/robojev-4b-v3":0.0048395274167548985,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.8172300099972277,"respan/span-02":0.7224741,"typesafe/jev-1.13":0.48,"JEV-27B-VL (10 frames)":0.7337805160695674,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.5546875}},{"suite":"unseen","id":"rbm-ood/usc_xarm/bbd59642-b65c-4f8d-9ab6-5ae9f5fe73cd","task":"Put blue cup in sink","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"bbd59642-b65c-4f8d-9ab6-5ae9f5fe73cd","predictions":{"RoboJev-27B":0.7299691405648602,"GPT-6 Astra":0.15,"GPT-6.1 Sol":0.15,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.9227199348354912,"TypeSafe Jev 1.14":0.63,"Perplexity Decider":0.8757885478091422,"Liquid D1":0.9919380092462978,"Mercury Decide":0.9626731097108832,"Cloudflare Clef":0.8633,"cloudflare/clef-flash":0.4825,"cloudflare/clef-omni":0.0841,"liquid/d1-ultra":0.8071467838982626,"open/intern-decision-4b":0.8748864949022742,"open/robojev-27b-v1@0.5":0.9100818290263152,"open/robojev-27b":null,"open/robojev-4b-v2":0.08579678054051716,"open/robojev-4b-v3@0.25":0.9669140577316284,"open/robojev-4b-v3@0.5":0.9368711827232762,"open/robojev-4b-v3@0.75":0.8892726892788834,"open/robojev-4b-v3":0.8573531996579977,"openai/gpt-6-luna-decisions":1.0,"perplexity/pplx-decider-flash-v1.2":0.9071037293677154,"respan/span-02":0.9226778,"typesafe/jev-1.13":0.75,"JEV-27B-VL (10 frames)":0.8519120512504538,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.84375}},{"suite":"unseen","id":"rbm-ood/usc_xarm/dab34346-c997-4a7b-b4c3-28f8124d0427","task":"Put blue cup in sink","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"dab34346-c997-4a7b-b4c3-28f8124d0427","predictions":{"RoboJev-27B":0.0056791027093295345,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.017096764557213612,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.042437454367756616,"Liquid D1":0.30735801686526387,"Mercury Decide":0.007577240595535943,"Cloudflare Clef":0.1737,"cloudflare/clef-flash":0.2591,"cloudflare/clef-omni":0.1278,"liquid/d1-ultra":0.03883944402042093,"open/intern-decision-4b":0.5624106420506467,"open/robojev-27b-v1@0.5":0.003089321951152287,"open/robojev-27b":null,"open/robojev-4b-v2":0.004106490957182719,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.008690106319066306,"open/robojev-4b-v3@0.75":0.008476838215708002,"open/robojev-4b-v3":0.008304581719395627,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.1188306928555832,"respan/span-02":0.23802638,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.0004995934981023219,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00860595703125}},{"suite":"unseen","id":"rbm-ood/usc_xarm/e5b8e128-8655-4f86-b68c-0e5d8647c68e","task":"Fold the towel in half","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"e5b8e128-8655-4f86-b68c-0e5d8647c68e","predictions":{"RoboJev-27B":0.6364400227788087,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.5857359185204958,"TypeSafe Jev 1.14":0.44,"Perplexity Decider":0.5300656986892036,"Liquid D1":0.9808759617117478,"Mercury Decide":0.32082130731838393,"Cloudflare Clef":0.4217,"cloudflare/clef-flash":0.3826,"cloudflare/clef-omni":0.2381,"liquid/d1-ultra":0.5855387423586069,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.9132668764789205,"open/robojev-27b":null,"open/robojev-4b-v2":0.9241418190100563,"open/robojev-4b-v3@0.25":0.622459352016449,"open/robojev-4b-v3@0.5":0.8707824477141304,"open/robojev-4b-v3@0.75":0.9198621986336036,"open/robojev-4b-v3":0.9027587968854268,"openai/gpt-6-luna-decisions":0.81,"perplexity/pplx-decider-flash-v1.2":0.6104174094890223,"respan/span-02":0.23946263,"typesafe/jev-1.13":0.62,"JEV-27B-VL (10 frames)":0.5060791993945816,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.78515625}},{"suite":"unseen","id":"rbm-ood/usc_xarm/ed87a481-15e0-4cbb-bf2c-05e8bd070c73","task":"Put the eggplant in the black bowl","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"ed87a481-15e0-4cbb-bf2c-05e8bd070c73","predictions":{"RoboJev-27B":0.5218747738332759,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.7205398926911615,"TypeSafe Jev 1.14":0.75,"Perplexity Decider":0.6779491496330025,"Liquid D1":0.9796676445054291,"Mercury Decide":0.9770226294209299,"Cloudflare Clef":0.6616,"cloudflare/clef-flash":0.3835,"cloudflare/clef-omni":0.1763,"liquid/d1-ultra":0.6092789268213934,"open/intern-decision-4b":0.7439389554145914,"open/robojev-27b-v1@0.5":0.6623705736021948,"open/robojev-27b":null,"open/robojev-4b-v2":0.031143833396690305,"open/robojev-4b-v3@0.25":0.18242551386356354,"open/robojev-4b-v3@0.5":0.0671334948723516,"open/robojev-4b-v3@0.75":0.038631651048510164,"open/robojev-4b-v3":0.04319701644612397,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.6898614944921544,"respan/span-02":0.24168055,"typesafe/jev-1.13":0.73,"JEV-27B-VL (10 frames)":0.7192317405983324,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.06298828125}},{"suite":"unseen","id":"rbm-ood/usc_xarm/f61a687b-c4d2-4bb8-9bc6-22d922c891e7","task":"Stack the green shape on the red cylinder","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"f61a687b-c4d2-4bb8-9bc6-22d922c891e7","predictions":{"RoboJev-27B":0.002688735776834418,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.007629603633739127,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.07833983741376525,"Liquid D1":0.21206880435710532,"Mercury Decide":0.005911068845298655,"Cloudflare Clef":0.2644,"cloudflare/clef-flash":0.229,"cloudflare/clef-omni":0.1172,"liquid/d1-ultra":0.21695809990668277,"open/intern-decision-4b":0.2806847685474584,"open/robojev-27b-v1@0.5":0.0001418541654296006,"open/robojev-27b":null,"open/robojev-4b-v2":0.002751490629587489,"open/robojev-4b-v3@0.25":0.06008664518594742,"open/robojev-4b-v3@0.5":0.009900079472737449,"open/robojev-4b-v3@0.75":0.004978582695254881,"open/robojev-4b-v3":0.003138491707937668,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2859343570747249,"respan/span-02":0.6894898,"typesafe/jev-1.13":0.14,"JEV-27B-VL (10 frames)":0.0003965424273600439,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.033203125}},{"suite":"unseen","id":"rbm-ood/usc_xarm/f7dea129-57fa-4f5d-8134-679626274759","task":"Put the banana on the red plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"f7dea129-57fa-4f5d-8134-679626274759","predictions":{"RoboJev-27B":0.0044504771605454775,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":7.153488297768146e-05,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.014372315050743384,"Liquid D1":0.7310585669110203,"Mercury Decide":0.0011695100017795118,"Cloudflare Clef":0.1436,"cloudflare/clef-flash":0.3431,"cloudflare/clef-omni":0.1744,"liquid/d1-ultra":0.03531702238514761,"open/intern-decision-4b":0.6798002499763626,"open/robojev-27b-v1@0.5":0.0005846652995221106,"open/robojev-27b":null,"open/robojev-4b-v2":0.016188347137528064,"open/robojev-4b-v3@0.25":0.042087726294994354,"open/robojev-4b-v3@0.5":0.02612421708095358,"open/robojev-4b-v3@0.75":0.019292242704938834,"open/robojev-4b-v3":0.021788411170123766,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.027178256965145572,"respan/span-02":0.050121546,"typesafe/jev-1.13":0.09,"JEV-27B-VL (10 frames)":2.5297777762355843e-05,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0169677734375}},{"suite":"unseen","id":"rbm-ood/usc_xarm/fb7d331c-0c73-4856-836f-42576128d95b","task":"Put the banana on the red plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"fb7d331c-0c73-4856-836f-42576128d95b","predictions":{"RoboJev-27B":0.3073014711459404,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.09607719975364967,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.31058839148853973,"Liquid D1":0.2814055953761018,"Mercury Decide":0.13296425222296632,"Cloudflare Clef":0.4392,"cloudflare/clef-flash":0.3475,"cloudflare/clef-omni":0.0612,"liquid/d1-ultra":0.23419873846123568,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.03440449759488159,"open/robojev-27b":null,"open/robojev-4b-v2":0.010419816599485524,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.017755273617510888,"open/robojev-4b-v3@0.75":0.011381877728436919,"open/robojev-4b-v3":0.009760866998496955,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.15150475607411673,"respan/span-02":0.16130424,"typesafe/jev-1.13":0.09,"JEV-27B-VL (10 frames)":0.12751467836336808,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.56640625}},{"suite":"unseen","id":"rbm-ood/usc_xarm/ffc600a7-d58a-40e9-b4c4-52da5596fbf8","task":"Put the banana on the red plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"usc_xarm","episode":"ffc600a7-d58a-40e9-b4c4-52da5596fbf8","predictions":{"RoboJev-27B":0.8656826672326857,"GPT-6 Astra":0.83,"GPT-6.1 Sol":0.91,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.740250404732747,"TypeSafe Jev 1.14":0.72,"Perplexity Decider":0.6074642082957701,"Liquid D1":0.9149009515124917,"Mercury Decide":0.5926665999540697,"Cloudflare Clef":0.693,"cloudflare/clef-flash":0.5616,"cloudflare/clef-omni":0.1305,"liquid/d1-ultra":0.3907210731786067,"open/intern-decision-4b":0.5469149563843178,"open/robojev-27b-v1@0.5":0.457955682971723,"open/robojev-27b":null,"open/robojev-4b-v2":0.006996270681650968,"open/robojev-4b-v3@0.25":0.3775406777858734,"open/robojev-4b-v3@0.5":0.1709446101989739,"open/robojev-4b-v3@0.75":0.08936373472637033,"open/robojev-4b-v3":0.038921036473713755,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.41299409105269325,"respan/span-02":0.92477745,"typesafe/jev-1.13":0.63,"JEV-27B-VL (10 frames)":0.8435264592278999,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.50390625}},{"suite":"unseen","id":"rbm-ood/utd_so101/0641becc-c8bb-4c92-a56e-8dbd946f465e","task":"Put the bread in the oven.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"0641becc-c8bb-4c92-a56e-8dbd946f465e","predictions":{"RoboJev-27B":0.7375283043843768,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.7,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.7031652632815423,"TypeSafe Jev 1.14":0.15,"Perplexity Decider":0.8191569751270428,"Liquid D1":0.9648551505674443,"Mercury Decide":0.8354835391516132,"Cloudflare Clef":0.7405,"cloudflare/clef-flash":0.7883,"cloudflare/clef-omni":0.7361,"liquid/d1-ultra":0.7993459322507966,"open/intern-decision-4b":0.8184242551251981,"open/robojev-27b-v1@0.5":0.8378215845739092,"open/robojev-27b":null,"open/robojev-4b-v2":0.06698650224956176,"open/robojev-4b-v3@0.25":0.9669140577316284,"open/robojev-4b-v3@0.5":0.8631975135960346,"open/robojev-4b-v3@0.75":0.2905205644506098,"open/robojev-4b-v3":0.15646321933638418,"openai/gpt-6-luna-decisions":0.92,"perplexity/pplx-decider-flash-v1.2":0.8622804359329315,"respan/span-02":0.9373937,"typesafe/jev-1.13":0.44,"JEV-27B-VL (10 frames)":0.7642856699963596,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.3203125}},{"suite":"unseen","id":"rbm-ood/utd_so101/17115224-7835-4a87-a7e0-f4fd6e7339f5","task":"Collect the fork to the yellow box.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"17115224-7835-4a87-a7e0-f4fd6e7339f5","predictions":{"RoboJev-27B":0.97752278916853,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.940317060406573,"TypeSafe Jev 1.14":0.82,"Perplexity Decider":0.9608161423314184,"Liquid D1":0.9950945939124053,"Mercury Decide":0.9980732650143008,"Cloudflare Clef":0.854,"cloudflare/clef-flash":0.8661,"cloudflare/clef-omni":0.4288,"liquid/d1-ultra":0.9508220457938104,"open/intern-decision-4b":0.9053865123447689,"open/robojev-27b-v1@0.5":0.973554453395604,"open/robojev-27b":null,"open/robojev-4b-v2":0.06424971190493048,"open/robojev-4b-v3@0.25":0.9875683188438416,"open/robojev-4b-v3@0.5":0.9871579519028945,"open/robojev-4b-v3@0.75":0.9282107321543306,"open/robojev-4b-v3":0.13612834674424493,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.9789092823593311,"respan/span-02":0.875789,"typesafe/jev-1.13":0.89,"JEV-27B-VL (10 frames)":0.9288196445008104,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.91015625}},{"suite":"unseen","id":"rbm-ood/utd_so101/2a671702-e614-4354-8098-29bc7a6b0068","task":"Put the pear in the yellow plate.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"2a671702-e614-4354-8098-29bc7a6b0068","predictions":{"RoboJev-27B":0.9853934801255425,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.9882090295103804,"TypeSafe Jev 1.14":0.83,"Perplexity Decider":0.9924587282833964,"Liquid D1":0.9959298631825974,"Mercury Decide":0.9986749773492493,"Cloudflare Clef":0.8966,"cloudflare/clef-flash":0.9236,"cloudflare/clef-omni":0.8749,"liquid/d1-ultra":0.9021558387917774,"open/intern-decision-4b":0.9156019658234928,"open/robojev-27b-v1@0.5":0.9907141689810172,"open/robojev-27b":null,"open/robojev-4b-v2":0.890729496785166,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.9683560447201516,"open/robojev-4b-v3@0.75":0.8330143287656493,"open/robojev-4b-v3":0.6575001774706176,"openai/gpt-6-luna-decisions":0.95,"perplexity/pplx-decider-flash-v1.2":0.9818934301477308,"respan/span-02":0.94490105,"typesafe/jev-1.13":0.91,"JEV-27B-VL (10 frames)":0.9745413273283408,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.8203125}},{"suite":"unseen","id":"rbm-ood/utd_so101/2cdf5d90-ad7d-495e-865c-bdc33dd74bf5","task":"Put the red cup on the purple coaster.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"2cdf5d90-ad7d-495e-865c-bdc33dd74bf5","predictions":{"RoboJev-27B":0.7523884670307186,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.86,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.7461303832340316,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.5428983095922449,"Liquid D1":0.06371499958557338,"Mercury Decide":0.24508502416032488,"Cloudflare Clef":0.3143,"cloudflare/clef-flash":0.2027,"cloudflare/clef-omni":0.1702,"liquid/d1-ultra":0.46304399869958657,"open/intern-decision-4b":0.43758935794935333,"open/robojev-27b-v1@0.5":0.9299350035190692,"open/robojev-27b":null,"open/robojev-4b-v2":0.0016856305131264125,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.029688941289226882,"open/robojev-4b-v3@0.75":0.02297736967873775,"open/robojev-4b-v3":0.013473327870331066,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.24730457860213423,"respan/span-02":0.096732005,"typesafe/jev-1.13":0.35,"JEV-27B-VL (10 frames)":0.595491554874352,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.71484375}},{"suite":"unseen","id":"rbm-ood/utd_so101/3ccee87c-e7db-41c1-9e07-b97110e95b92","task":"Put the eraser to the blue pencil box.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"3ccee87c-e7db-41c1-9e07-b97110e95b92","predictions":{"RoboJev-27B":0.9103423690840032,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.75,"JEV-27B-VL":0.8752757958122362,"TypeSafe Jev 1.14":0.77,"Perplexity Decider":0.8431705908717053,"Liquid D1":0.9928785718864359,"Mercury Decide":0.9706877713155613,"Cloudflare Clef":0.7513,"cloudflare/clef-flash":0.6692,"cloudflare/clef-omni":0.6705,"liquid/d1-ultra":0.6209651777561939,"open/intern-decision-4b":0.799028310455341,"open/robojev-27b-v1@0.5":0.9651313759811629,"open/robojev-27b":null,"open/robojev-4b-v2":0.00731334505501762,"open/robojev-4b-v3@0.25":0.9399133324623108,"open/robojev-4b-v3@0.5":0.4345875784292984,"open/robojev-4b-v3@0.75":0.03444519627897428,"open/robojev-4b-v3":0.01146957225399579,"openai/gpt-6-luna-decisions":0.84,"perplexity/pplx-decider-flash-v1.2":0.8110054077977021,"respan/span-02":0.9469455,"typesafe/jev-1.13":0.83,"JEV-27B-VL (10 frames)":0.8414208286747363,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.5078125}},{"suite":"unseen","id":"rbm-ood/utd_so101/5296a584-bd36-43a3-9b64-58980b7814da","task":"Press the button.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"5296a584-bd36-43a3-9b64-58980b7814da","predictions":{"RoboJev-27B":0.8955641603791504,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":0.6492955835296644,"TypeSafe Jev 1.14":0.72,"Perplexity Decider":0.8055466804992126,"Liquid D1":0.6791786861878392,"Mercury Decide":0.9324533074525657,"Cloudflare Clef":0.5806,"cloudflare/clef-flash":0.4864,"cloudflare/clef-omni":0.1417,"liquid/d1-ultra":0.6325127183904117,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.9680580498558067,"open/robojev-27b":null,"open/robojev-4b-v2":0.3796411992131174,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.22270012535630726,"open/robojev-4b-v3@0.75":0.20277377238617383,"open/robojev-4b-v3":0.13612834674424493,"openai/gpt-6-luna-decisions":0.71,"perplexity/pplx-decider-flash-v1.2":0.29888911122677053,"respan/span-02":0.6381668,"typesafe/jev-1.13":0.55,"JEV-27B-VL (10 frames)":0.7554345314879405,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00885009765625}},{"suite":"unseen","id":"rbm-ood/utd_so101/65d1db25-46ce-4175-8b52-fffb517b49bf","task":"Put the pear in the yellow plate.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"65d1db25-46ce-4175-8b52-fffb517b49bf","predictions":{"RoboJev-27B":0.0017434731433478535,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.01,"JEV-27B-VL":2.1847510093212128e-05,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.0083745431858827,"Liquid D1":0.000969751801763804,"Mercury Decide":0.0003150388278308255,"Cloudflare Clef":0.0539,"cloudflare/clef-flash":0.1346,"cloudflare/clef-omni":0.0831,"liquid/d1-ultra":0.022938864352414566,"open/intern-decision-4b":0.10592235395880453,"open/robojev-27b-v1@0.5":6.737574207444498e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.0014746525778226533,"open/robojev-4b-v3@0.25":0.006692850962281227,"open/robojev-4b-v3@0.5":0.0016895888785682799,"open/robojev-4b-v3@0.75":0.0010633807184710219,"open/robojev-4b-v3":0.00106063530615271,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.031399001384187254,"respan/span-02":0.066218875,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.0010407576963321309,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00150299072265625}},{"suite":"unseen","id":"rbm-ood/utd_so101/6dcbfb2a-a612-433d-a64c-c3083a32337e","task":"Add pepper to the green bowl.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"6dcbfb2a-a612-433d-a64c-c3083a32337e","predictions":{"RoboJev-27B":0.6977581930756894,"GPT-6 Astra":0.81,"GPT-6.1 Sol":0.78,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.3097538282682883,"TypeSafe Jev 1.14":0.21,"Perplexity Decider":0.24690528266194894,"Liquid D1":0.17328820592932656,"Mercury Decide":0.18242552380635632,"Cloudflare Clef":0.4563,"cloudflare/clef-flash":0.5043,"cloudflare/clef-omni":0.2499,"liquid/d1-ultra":0.2617952535625818,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.18440997654014626,"open/robojev-27b":null,"open/robojev-4b-v2":0.0025170615300917137,"open/robojev-4b-v3@0.25":0.09534946084022522,"open/robojev-4b-v3@0.5":0.02612421708095358,"open/robojev-4b-v3@0.75":0.016188346495106164,"open/robojev-4b-v3":0.01499717745111633,"openai/gpt-6-luna-decisions":0.06,"perplexity/pplx-decider-flash-v1.2":0.4076709598535394,"respan/span-02":0.6277677,"typesafe/jev-1.13":0.26,"JEV-27B-VL (10 frames)":0.3591906871174631,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.04150390625}},{"suite":"unseen","id":"rbm-ood/utd_so101/72c73b9d-bc33-4181-804d-bb3096034da4","task":"Put the marker into the pen cup.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"72c73b9d-bc33-4181-804d-bb3096034da4","predictions":{"RoboJev-27B":0.002435244371928488,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.01,"JEV-27B-VL":0.0037853779769958895,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.007306173326502317,"Liquid D1":0.02442308792384301,"Mercury Decide":0.00037998446876388826,"Cloudflare Clef":0.0592,"cloudflare/clef-flash":0.2085,"cloudflare/clef-omni":0.0729,"liquid/d1-ultra":0.014832383804206838,"open/intern-decision-4b":0.14720923592665844,"open/robojev-27b-v1@0.5":0.0005578788933781982,"open/robojev-27b":null,"open/robojev-4b-v2":0.0020145213081092066,"open/robojev-4b-v3@0.25":0.01590639166533947,"open/robojev-4b-v3@0.5":0.0037133326112963453,"open/robojev-4b-v3@0.75":0.0025929030441612317,"open/robojev-4b-v3":0.0022671624120110317,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1438758738934112,"respan/span-02":0.058172442,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.0030567837770563424,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00136566162109375}},{"suite":"unseen","id":"rbm-ood/utd_so101/77f40402-ef04-45b1-ae7c-9be90a6d80dc","task":"Collect the fork to the yellow box.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"77f40402-ef04-45b1-ae7c-9be90a6d80dc","predictions":{"RoboJev-27B":0.004085846603021986,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0076881426940850935,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.015703155939064992,"Liquid D1":0.2942149597859341,"Mercury Decide":0.0014103583733232853,"Cloudflare Clef":0.2055,"cloudflare/clef-flash":0.2297,"cloudflare/clef-omni":0.2167,"liquid/d1-ultra":0.03531702258563878,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.0003031790348034893,"open/robojev-27b":null,"open/robojev-4b-v2":0.0020145213081092066,"open/robojev-4b-v3@0.25":0.022977370768785477,"open/robojev-4b-v3@0.5":0.003964844872971652,"open/robojev-4b-v3@0.75":0.00244343308696661,"open/robojev-4b-v3":0.0020341273969387797,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.04771478594910886,"respan/span-02":0.22310883,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.012361355096123648,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00193023681640625}},{"suite":"unseen","id":"rbm-ood/utd_so101/805de0a8-f4cf-490d-8e2f-bc6cb70a0130","task":"Stack the green block on the red block.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"805de0a8-f4cf-490d-8e2f-bc6cb70a0130","predictions":{"RoboJev-27B":0.018200367390840386,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":0.2479901091861985,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.30513268369759067,"Liquid D1":0.039638839100970026,"Mercury Decide":0.03308597969964969,"Cloudflare Clef":0.1267,"cloudflare/clef-flash":0.133,"cloudflare/clef-omni":0.0853,"liquid/d1-ultra":0.049177952555188205,"open/intern-decision-4b":0.10012611628383591,"open/robojev-27b-v1@0.5":0.027662094205693526,"open/robojev-27b":null,"open/robojev-4b-v2":0.0009029603038478018,"open/robojev-4b-v3@0.25":0.01243165135383606,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.005946149584938689,"open/robojev-4b-v3":0.007064018099624773,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.0232116772420269,"respan/span-02":0.090713456,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.14283122094166115,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2431640625}},{"suite":"unseen","id":"rbm-ood/utd_so101/83cbb89e-6649-4456-9d93-9a50670e51b3","task":"Put the bread in the oven.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"83cbb89e-6649-4456-9d93-9a50670e51b3","predictions":{"RoboJev-27B":0.0041707839188762615,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.006750961929567011,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.022570542279586985,"Liquid D1":0.1645164628965632,"Mercury Decide":0.0019267348388409885,"Cloudflare Clef":0.2622,"cloudflare/clef-flash":0.3021,"cloudflare/clef-omni":0.3327,"liquid/d1-ultra":0.04917795338068897,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.0009839407519580388,"open/robojev-27b":null,"open/robojev-4b-v2":0.005858834000676852,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.008141294289513608,"open/robojev-4b-v3@0.75":0.004978582695254881,"open/robojev-4b-v3":0.004584702275672031,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.09249015251902616,"respan/span-02":0.054517273,"typesafe/jev-1.13":0.03,"JEV-27B-VL (10 frames)":0.016078879458569294,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00096893310546875}},{"suite":"unseen","id":"rbm-ood/utd_so101/a5bdb049-3422-4fbb-bfe7-2c637057a6fd","task":"Put the red bowl on the blue plate.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"a5bdb049-3422-4fbb-bfe7-2c637057a6fd","predictions":{"RoboJev-27B":0.000798496608701173,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.01,"JEV-27B-VL":0.00013119407073614,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.0065315713775797885,"Liquid D1":0.00460957120508249,"Mercury Decide":0.0002453695271488881,"Cloudflare Clef":0.0336,"cloudflare/clef-flash":0.1805,"cloudflare/clef-omni":0.0666,"liquid/d1-ultra":0.018012011529892867,"open/intern-decision-4b":0.08937422170979005,"open/robojev-27b-v1@0.5":0.00025446489438199764,"open/robojev-27b":null,"open/robojev-4b-v2":0.0010793060165100975,"open/robojev-4b-v3@0.25":0.004070138093084097,"open/robojev-4b-v3@0.5":0.0016895888785682799,"open/robojev-4b-v3@0.75":0.0011976561657233782,"open/robojev-4b-v3":0.0011198072393420323,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.008101911159194723,"respan/span-02":0.0620345,"typesafe/jev-1.13":0.03,"JEV-27B-VL (10 frames)":0.00015794922580076855,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00193023681640625}},{"suite":"unseen","id":"rbm-ood/utd_so101/af70eeb2-e86d-45b7-a5fb-a2793c736072","task":"Add pepper to the green bowl.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"af70eeb2-e86d-45b7-a5fb-a2793c736072","predictions":{"RoboJev-27B":0.124357833335726,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.06320832222986536,"TypeSafe Jev 1.14":0.17,"Perplexity Decider":0.1878669579180471,"Liquid D1":0.2689414213699951,"Mercury Decide":0.09534945782972029,"Cloudflare Clef":0.2917,"cloudflare/clef-flash":0.3058,"cloudflare/clef-omni":0.1983,"liquid/d1-ultra":0.06809489325539766,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.05520305871481307,"open/robojev-27b":null,"open/robojev-4b-v2":0.0023025598229782147,"open/robojev-4b-v3@0.25":0.0534033328294754,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.0032876613688676065,"open/robojev-4b-v3":0.002667578431318334,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.12143020003031518,"respan/span-02":0.27852464,"typesafe/jev-1.13":0.12,"JEV-27B-VL (10 frames)":0.04095864686696754,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0013275146484375}},{"suite":"unseen","id":"rbm-ood/utd_so101/b48899a2-969c-4fa0-9ecb-827456ff935e","task":"Stack the green block on the red block.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"b48899a2-969c-4fa0-9ecb-827456ff935e","predictions":{"RoboJev-27B":0.5962878517744912,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.87,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.49994098987890373,"TypeSafe Jev 1.14":0.41,"Perplexity Decider":0.4971387698646225,"Liquid D1":0.679178699175393,"Mercury Decide":0.1480471980316895,"Cloudflare Clef":0.3212,"cloudflare/clef-flash":0.3314,"cloudflare/clef-omni":0.1577,"liquid/d1-ultra":0.5735104048478977,"open/intern-decision-4b":0.6518947636686268,"open/robojev-27b-v1@0.5":0.9336582785319246,"open/robojev-27b":null,"open/robojev-4b-v2":0.0790476748344352,"open/robojev-4b-v3@0.25":0.9399133324623108,"open/robojev-4b-v3@0.5":0.9328665051276483,"open/robojev-4b-v3@0.75":0.7972262276138262,"open/robojev-4b-v3":0.472852806132433,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.7511637899135237,"respan/span-02":0.69739366,"typesafe/jev-1.13":0.37,"JEV-27B-VL (10 frames)":0.615714872961019,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.275390625}},{"suite":"unseen","id":"rbm-ood/utd_so101/c8ec8598-f543-4765-9b0a-f573d0fd0b88","task":"Press the button.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"c8ec8598-f543-4765-9b0a-f573d0fd0b88","predictions":{"RoboJev-27B":0.7536573795130037,"GPT-6 Astra":0.06,"GPT-6.1 Sol":0.07,"Claude Opus 5.5":0.25,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.18440687520876878,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.20819944493956366,"Liquid D1":0.21206879439743004,"Mercury Decide":0.10669058968506456,"Cloudflare Clef":0.317,"cloudflare/clef-flash":0.2399,"cloudflare/clef-omni":0.1043,"liquid/d1-ultra":0.25236787272174804,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.10823964480638251,"open/robojev-27b":null,"open/robojev-4b-v2":0.04990557889898353,"open/robojev-4b-v3@0.25":0.07585817575454712,"open/robojev-4b-v3@0.5":0.059347834814291,"open/robojev-4b-v3@0.75":0.02297736967873775,"open/robojev-4b-v3":0.010869457225645628,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.19788806534437492,"respan/span-02":0.04770471,"typesafe/jev-1.13":0.1,"JEV-27B-VL (10 frames)":0.5345530918957505,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00141143798828125}},{"suite":"unseen","id":"rbm-ood/utd_so101/d5c4164a-06b4-4bf0-871e-bbf6c736190a","task":"Put the red cup on the purple coaster.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"d5c4164a-06b4-4bf0-871e-bbf6c736190a","predictions":{"RoboJev-27B":0.003982249508187564,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0012421812382331253,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.02528740037187241,"Liquid D1":0.0062899032079716715,"Mercury Decide":0.001810210699731994,"Cloudflare Clef":0.0625,"cloudflare/clef-flash":0.1942,"cloudflare/clef-omni":0.1637,"liquid/d1-ultra":0.029173324633752523,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.00036025499281495233,"open/robojev-27b":null,"open/robojev-4b-v2":0.0010793060165100975,"open/robojev-4b-v3@0.25":0.009708477184176445,"open/robojev-4b-v3@0.5":0.0037133326112963453,"open/robojev-4b-v3@0.75":0.0021697908424400778,"open/robojev-4b-v3":0.0019267345803236512,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.23592864067332997,"respan/span-02":0.024445504,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.0019688864254243737,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.046142578125}},{"suite":"unseen","id":"rbm-ood/utd_so101/dfb9e90c-75a0-4eb2-83c3-4e38cb101e0e","task":"Put the marker into the pen cup.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"dfb9e90c-75a0-4eb2-83c3-4e38cb101e0e","predictions":{"RoboJev-27B":0.9218027879166248,"GPT-6 Astra":0.91,"GPT-6.1 Sol":0.9,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.45,"JEV-27B-VL":0.5460238654992312,"TypeSafe Jev 1.14":0.29,"Perplexity Decider":0.440829840198239,"Liquid D1":0.7057850216484838,"Mercury Decide":0.679178699175393,"Cloudflare Clef":0.3211,"cloudflare/clef-flash":0.3521,"cloudflare/clef-omni":0.086,"liquid/d1-ultra":0.333787150806788,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.7906688852879286,"open/robojev-27b":null,"open/robojev-4b-v2":0.01138187822152329,"open/robojev-4b-v3@0.25":0.06754669547080994,"open/robojev-4b-v3@0.5":0.03828411009766295,"open/robojev-4b-v3@0.75":0.03444519627897428,"open/robojev-4b-v3":0.03155642361885442,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.43509899409313796,"respan/span-02":0.2361166,"typesafe/jev-1.13":0.32,"JEV-27B-VL (10 frames)":0.6868725769342398,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.60546875}},{"suite":"unseen","id":"rbm-ood/utd_so101/e5088127-7e1a-4526-9927-54e2e8f4b5b5","task":"Put the red bowl on the blue plate.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"e5088127-7e1a-4526-9927-54e2e8f4b5b5","predictions":{"RoboJev-27B":0.9909486968140983,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.9,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.9873252626904847,"TypeSafe Jev 1.14":0.86,"Perplexity Decider":0.9894317503629562,"Liquid D1":0.9992445942702572,"Mercury Decide":0.9984988176308862,"Cloudflare Clef":0.953,"cloudflare/clef-flash":0.9107,"cloudflare/clef-omni":0.8918,"liquid/d1-ultra":0.9573023608562846,"open/intern-decision-4b":0.8815938286018441,"open/robojev-27b-v1@0.5":0.9928967346215816,"open/robojev-27b":null,"open/robojev-4b-v2":0.008730681628235537,"open/robojev-4b-v3@0.25":0.9875683188438416,"open/robojev-4b-v3@0.5":0.9703110587107732,"open/robojev-4b-v3@0.75":0.756014627783845,"open/robojev-4b-v3":0.3424998225293823,"openai/gpt-6-luna-decisions":0.99,"perplexity/pplx-decider-flash-v1.2":0.9865723769542246,"respan/span-02":0.9300789,"typesafe/jev-1.13":0.95,"JEV-27B-VL (10 frames)":0.962865498455664,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.85546875}},{"suite":"unseen","id":"rbm-ood/utd_so101/e838f14d-2c55-45e2-9e00-d8883880e9af","task":"Put the eraser to the blue pencil box.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101","episode":"e838f14d-2c55-45e2-9e00-d8883880e9af","predictions":{"RoboJev-27B":0.0014425479925773436,"GPT-6 Astra":0.005,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.00020744892488957391,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.006062531103897556,"Liquid D1":0.00806198980038623,"Mercury Decide":0.000588408701901969,"Cloudflare Clef":0.1346,"cloudflare/clef-flash":0.1634,"cloudflare/clef-omni":0.0855,"liquid/d1-ultra":0.030604417452612675,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":6.676405757009947e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.003927901641619978,"open/robojev-4b-v3@0.25":0.01243165135383606,"open/robojev-4b-v3@0.5":0.004519892642389456,"open/robojev-4b-v3@0.75":0.0041678002213721265,"open/robojev-4b-v3":0.0025268270309959213,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.042779509307350284,"respan/span-02":0.072300166,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.001919534275481237,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00102996826171875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/07bc3a74-d939-4f0e-b171-e2ffc1e08d22","task":"Put the apple in the yellow plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"07bc3a74-d939-4f0e-b171-e2ffc1e08d22","predictions":{"RoboJev-27B":0.00048579079577531153,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.001271180810412392,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.012967523718301259,"Liquid D1":0.02033235423310517,"Mercury Decide":0.0011695100909887293,"Cloudflare Clef":0.0422,"cloudflare/clef-flash":0.1462,"cloudflare/clef-omni":0.0758,"liquid/d1-ultra":0.037037987370828376,"open/intern-decision-4b":0.13214384255458153,"open/robojev-27b-v1@0.5":2.6980911855381237e-05,"open/robojev-27b":null,"open/robojev-4b-v2":0.0032876614041202805,"open/robojev-4b-v3@0.25":0.01798621006309986,"open/robojev-4b-v3@0.5":0.0051522412018618095,"open/robojev-4b-v3@0.75":0.0037017607703716303,"open/robojev-4b-v3":0.0023934843568307186,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.05377962132837775,"respan/span-02":0.09318316,"typesafe/jev-1.13":0.03,"JEV-27B-VL (10 frames)":0.0002673517150162546,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0038299560546875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/090634f8-db11-444b-bb37-01f6fea9d0fe","task":"Put the red cup on the purple coaster","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"090634f8-db11-444b-bb37-01f6fea9d0fe","predictions":{"RoboJev-27B":0.0029574084190462386,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":8.193503496867887e-05,"TypeSafe Jev 1.14":0.04,"Perplexity Decider":0.01975685336237611,"Liquid D1":0.24508501313237172,"Mercury Decide":0.0006263341079753964,"Cloudflare Clef":0.065,"cloudflare/clef-flash":0.1744,"cloudflare/clef-omni":0.1056,"liquid/d1-ultra":0.046920385288568144,"open/intern-decision-4b":0.5624106420506467,"open/robojev-27b-v1@0.5":0.0002505567727636995,"open/robojev-27b":null,"open/robojev-4b-v2":0.01929224350793923,"open/robojev-4b-v3@0.25":0.01798621006309986,"open/robojev-4b-v3@0.5":0.010566189227213266,"open/robojev-4b-v3@0.75":0.01011736424150334,"open/robojev-4b-v3":0.009249319533522623,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.7671625283999874,"respan/span-02":0.05233614,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.00042576991955626067,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.4921875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/1a732a0b-d548-42f3-bbb3-066d78dfe8ad","task":"Put the bread in the oven","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"1a732a0b-d548-42f3-bbb3-066d78dfe8ad","predictions":{"RoboJev-27B":0.6176151047560211,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.13,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.6279698438585501,"TypeSafe Jev 1.14":0.42,"Perplexity Decider":0.64061872926269,"Liquid D1":0.9883127409715955,"Mercury Decide":0.37754066879814546,"Cloudflare Clef":0.6933,"cloudflare/clef-flash":0.8679,"cloudflare/clef-omni":0.6599,"liquid/d1-ultra":0.8291578031974798,"open/intern-decision-4b":0.8815938286018441,"open/robojev-27b-v1@0.5":0.833364995931788,"open/robojev-27b":null,"open/robojev-4b-v2":0.09690095299759889,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.9328665051276483,"open/robojev-4b-v3@0.75":0.8157922105403737,"open/robojev-4b-v3":0.6199015702350262,"openai/gpt-6-luna-decisions":0.91,"perplexity/pplx-decider-flash-v1.2":0.9399987148806221,"respan/span-02":0.96460927,"typesafe/jev-1.13":0.51,"JEV-27B-VL (10 frames)":0.5881797174504899,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.10498046875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/20cf5a1a-8e34-43b8-bbc2-9c4505b1d3cb","task":"Press the button","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"20cf5a1a-8e34-43b8-bbc2-9c4505b1d3cb","predictions":{"RoboJev-27B":0.17046924321299017,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.1531460198959164,"TypeSafe Jev 1.14":0.21,"Perplexity Decider":0.09413062653404887,"Liquid D1":0.2689414272294874,"Mercury Decide":0.13296423160844623,"Cloudflare Clef":0.3565,"cloudflare/clef-flash":0.2066,"cloudflare/clef-omni":0.1375,"liquid/d1-ultra":0.24316815310838966,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.014493793060149496,"open/robojev-27b":null,"open/robojev-4b-v2":0.1381957315129781,"open/robojev-4b-v3@0.25":0.2689414322376251,"open/robojev-4b-v3@0.5":0.1618215453479303,"open/robojev-4b-v3@0.75":0.15107550847556014,"open/robojev-4b-v3":0.15646321933638418,"openai/gpt-6-luna-decisions":0.9,"perplexity/pplx-decider-flash-v1.2":0.3453594341037369,"respan/span-02":0.10223536,"typesafe/jev-1.13":0.24,"JEV-27B-VL (10 frames)":0.10102149631718976,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.003936767578125}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/2626b326-8dd6-4b70-b838-12671c047510","task":"Put the eraser to the blue pencil box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"2626b326-8dd6-4b70-b838-12671c047510","predictions":{"RoboJev-27B":0.01508816543679918,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.014090979175883886,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.03855258068651488,"Liquid D1":0.02442308845640904,"Mercury Decide":0.010986943784269256,"Cloudflare Clef":0.1197,"cloudflare/clef-flash":0.2195,"cloudflare/clef-omni":0.0835,"liquid/d1-ultra":0.049177952555188205,"open/intern-decision-4b":0.5156793174877148,"open/robojev-27b-v1@0.5":0.004680145410417504,"open/robojev-27b":null,"open/robojev-4b-v2":0.031143833396690305,"open/robojev-4b-v3@0.25":0.02595735713839531,"open/robojev-4b-v3@0.5":0.009900079472737449,"open/robojev-4b-v3@0.75":0.005946149584938689,"open/robojev-4b-v3":0.005108442412304043,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.06195153744469375,"respan/span-02":0.026000602,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.024303229646257255,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0179443359375}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/2a7ff11c-dedc-430c-8a37-02146dbf8840","task":"Put the marker into the pen cup","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"2a7ff11c-dedc-430c-8a37-02146dbf8840","predictions":{"RoboJev-27B":0.7207636683654834,"GPT-6 Astra":0.25,"GPT-6.1 Sol":0.18,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.784779984173432,"TypeSafe Jev 1.14":0.43,"Perplexity Decider":0.6319770054266313,"Liquid D1":0.9553191325895679,"Mercury Decide":0.8933093982432729,"Cloudflare Clef":0.6264,"cloudflare/clef-flash":0.652,"cloudflare/clef-omni":0.3135,"liquid/d1-ultra":0.3560898041822152,"open/intern-decision-4b":0.7193152314525416,"open/robojev-27b-v1@0.5":0.8502676387436806,"open/robojev-27b":null,"open/robojev-4b-v2":0.12300397797247992,"open/robojev-4b-v3@0.25":0.9149009585380554,"open/robojev-4b-v3@0.5":0.7657040237782665,"open/robojev-4b-v3@0.75":0.5738603834212919,"open/robojev-4b-v3":0.6451587915501215,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.8248783573382058,"respan/span-02":0.91287196,"typesafe/jev-1.13":0.65,"JEV-27B-VL (10 frames)":0.6904213335222003,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.8203125}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/2d01b3f0-fb7b-4cb2-8d11-1b7def16e489","task":"Collect the fork to the yellow box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"2d01b3f0-fb7b-4cb2-8d11-1b7def16e489","predictions":{"RoboJev-27B":0.03761222165520687,"GPT-6 Astra":0.78,"GPT-6.1 Sol":0.73,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.4538591167627615,"TypeSafe Jev 1.14":0.14,"Perplexity Decider":0.3474167765373369,"Liquid D1":0.5926665999540697,"Mercury Decide":0.06008665438181589,"Cloudflare Clef":0.1984,"cloudflare/clef-flash":0.1795,"cloudflare/clef-omni":0.1504,"liquid/d1-ultra":0.1573075083680267,"open/intern-decision-4b":0.1910858322004182,"open/robojev-27b-v1@0.5":0.2681237376034691,"open/robojev-27b":null,"open/robojev-4b-v2":0.02506949741812164,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.04625107524610428,"open/robojev-4b-v3@0.75":0.02435227726532882,"open/robojev-4b-v3":0.01499717745111633,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.22315627292353063,"respan/span-02":0.08146393,"typesafe/jev-1.13":0.3,"JEV-27B-VL (10 frames)":0.013130652947669878,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.037841796875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/3004041d-747f-4425-86e4-bfb5938617b0","task":"Put the apple in the yellow plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"3004041d-747f-4425-86e4-bfb5938617b0","predictions":{"RoboJev-27B":0.9792052151881813,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.9710270549550446,"TypeSafe Jev 1.14":0.87,"Perplexity Decider":0.9794748002190605,"Liquid D1":0.9971990724658043,"Mercury Decide":0.998498817850754,"Cloudflare Clef":0.9472,"cloudflare/clef-flash":0.8889,"cloudflare/clef-omni":0.3084,"liquid/d1-ultra":0.9407227444007749,"open/intern-decision-4b":0.8527907640733415,"open/robojev-27b-v1@0.5":0.9719576644878786,"open/robojev-27b":null,"open/robojev-4b-v2":0.7001924251222287,"open/robojev-4b-v3@0.25":0.9820137619972229,"open/robojev-4b-v3@0.5":0.972148766331303,"open/robojev-4b-v3@0.75":0.9320774407500154,"open/robojev-4b-v3":0.7772998505135637,"openai/gpt-6-luna-decisions":0.92,"perplexity/pplx-decider-flash-v1.2":0.978253903312236,"respan/span-02":0.9608116,"typesafe/jev-1.13":0.91,"JEV-27B-VL (10 frames)":0.9326163100261795,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.8046875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/300a162d-734f-4699-9379-8b8b23d1dc58","task":"Collect the fork to the yellow box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"300a162d-734f-4699-9379-8b8b23d1dc58","predictions":{"RoboJev-27B":0.00823336394450917,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.021045270195520657,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.043385030634462626,"Liquid D1":0.2689414213699951,"Mercury Decide":0.022977370537254904,"Cloudflare Clef":0.1131,"cloudflare/clef-flash":0.1954,"cloudflare/clef-omni":0.2391,"liquid/d1-ultra":0.12189698167300049,"open/intern-decision-4b":0.2935240287234267,"open/robojev-27b-v1@0.5":0.003599516915524915,"open/robojev-27b":null,"open/robojev-4b-v2":0.008730681628235537,"open/robojev-4b-v3@0.25":0.022977370768785477,"open/robojev-4b-v3@0.5":0.007144725422878838,"open/robojev-4b-v3@0.75":0.005946149584938689,"open/robojev-4b-v3":0.0041144364846599805,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.09184090355015524,"respan/span-02":0.051678173,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.005925746343366728,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0225830078125}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/30d09c33-6997-430d-af14-e8260fb88b45","task":"Put the bread in the oven","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"30d09c33-6997-430d-af14-e8260fb88b45","predictions":{"RoboJev-27B":0.8384478175506613,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.18,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.8024335689185014,"TypeSafe Jev 1.14":0.46,"Perplexity Decider":0.8402516161727313,"Liquid D1":0.9706877693546394,"Mercury Decide":0.9399133468805266,"Cloudflare Clef":0.865,"cloudflare/clef-flash":0.7273,"cloudflare/clef-omni":0.7314,"liquid/d1-ultra":0.8553419821885395,"open/intern-decision-4b":0.8748864949022742,"open/robojev-27b-v1@0.5":0.9517396303737271,"open/robojev-27b":null,"open/robojev-4b-v2":0.14359896340218653,"open/robojev-4b-v3@0.25":0.977022647857666,"open/robojev-4b-v3@0.5":0.9442201868171092,"open/robojev-4b-v3@0.75":0.787433462339429,"open/robojev-4b-v3":0.25219182149741376,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.8799806171534155,"respan/span-02":0.95546234,"typesafe/jev-1.13":0.56,"JEV-27B-VL (10 frames)":0.6936031979353576,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2734375}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/4533811a-dca7-4155-9c99-a877c9ff42c7","task":"Stack the green block on the red block","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"4533811a-dca7-4155-9c99-a877c9ff42c7","predictions":{"RoboJev-27B":0.0036630369353317076,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.00895708313587258,"TypeSafe Jev 1.14":0.08,"Perplexity Decider":0.02685669107418608,"Liquid D1":0.03514484387432486,"Mercury Decide":0.009708475371185328,"Cloudflare Clef":0.0821,"cloudflare/clef-flash":0.2014,"cloudflare/clef-omni":0.1281,"liquid/d1-ultra":0.07463358149158525,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.00031199419859487634,"open/robojev-27b":null,"open/robojev-4b-v2":0.04583824899717374,"open/robojev-4b-v3@0.25":0.02931223064661026,"open/robojev-4b-v3@0.5":0.013703364243695216,"open/robojev-4b-v3@0.75":0.010731211960485985,"open/robojev-4b-v3":0.010869457225645628,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.0782922698466044,"respan/span-02":0.0653447,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.0012769670893172003,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006103515625}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/473480d3-c008-4826-bd0e-15eb01d64a1c","task":"Add pepper to the green bowl","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"473480d3-c008-4826-bd0e-15eb01d64a1c","predictions":{"RoboJev-27B":0.6562599610690384,"GPT-6 Astra":0.9,"GPT-6.1 Sol":0.9,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":0.6666265717535418,"TypeSafe Jev 1.14":0.5,"Perplexity Decider":0.4469093246971382,"Liquid D1":0.5621765008857981,"Mercury Decide":0.8807970873650403,"Cloudflare Clef":0.391,"cloudflare/clef-flash":0.5826,"cloudflare/clef-omni":0.1929,"liquid/d1-ultra":0.4876613324012321,"open/intern-decision-4b":0.3340072352673295,"open/robojev-27b-v1@0.5":0.5052679615909411,"open/robojev-27b":null,"open/robojev-4b-v2":0.008352675304716173,"open/robojev-4b-v3@0.25":0.622459352016449,"open/robojev-4b-v3@0.5":0.8552413411866893,"open/robojev-4b-v3@0.75":0.7448684965407143,"open/robojev-4b-v3":0.7158387184205455,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.48264628591167213,"respan/span-02":0.09487145,"typesafe/jev-1.13":0.55,"JEV-27B-VL (10 frames)":0.640405848105359,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0341796875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/5050e6b9-0a55-424b-8e20-20fd993fa069","task":"Put the marker into the pen cup","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"5050e6b9-0a55-424b-8e20-20fd993fa069","predictions":{"RoboJev-27B":0.9808732502201263,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.97980067479005,"TypeSafe Jev 1.14":0.8,"Perplexity Decider":0.9854623167903226,"Liquid D1":0.9830850832022883,"Mercury Decide":0.9964063979254659,"Cloudflare Clef":0.7324,"cloudflare/clef-flash":0.4854,"cloudflare/clef-omni":0.3381,"liquid/d1-ultra":0.9573023571279813,"open/intern-decision-4b":0.8275619327448428,"open/robojev-27b-v1@0.5":0.9931149814540647,"open/robojev-27b":null,"open/robojev-4b-v2":0.72753320017948,"open/robojev-4b-v3@0.25":0.9626730680465698,"open/robojev-4b-v3@0.5":0.961715889902337,"open/robojev-4b-v3@0.75":0.9320774407500154,"open/robojev-4b-v3":0.9278650639695798,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.9410281696363907,"respan/span-02":0.15174894,"typesafe/jev-1.13":0.88,"JEV-27B-VL (10 frames)":0.9723107167649641,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.80078125}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/5b9f758e-0a16-42d8-9558-9e0a4bea6f9c","task":"Add pepper to the green bowl","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"5b9f758e-0a16-42d8-9558-9e0a4bea6f9c","predictions":{"RoboJev-27B":0.026170662047898027,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.02727630044276095,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.01668138686090551,"Liquid D1":0.031143831883656593,"Mercury Decide":0.042087723109535534,"Cloudflare Clef":0.0693,"cloudflare/clef-flash":0.1209,"cloudflare/clef-omni":0.1438,"liquid/d1-ultra":0.05658366023666175,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.0014844786994856595,"open/robojev-27b":null,"open/robojev-4b-v2":0.005361080321059209,"open/robojev-4b-v3@0.25":0.020332353189587593,"open/robojev-4b-v3@0.5":0.006692850574775813,"open/robojev-4b-v3@0.75":0.003927901618504033,"open/robojev-4b-v3":0.0023934843568307186,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.0662418210235936,"respan/span-02":0.027455013,"typesafe/jev-1.13":0.12,"JEV-27B-VL (10 frames)":0.016384644233642113,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00433349609375}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/5d780693-a56a-4f4c-aa1f-bf816ae0eccf","task":"Collect the fork to the yellow box","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"5d780693-a56a-4f4c-aa1f-bf816ae0eccf","predictions":{"RoboJev-27B":0.9429422006764452,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.8212457286007666,"TypeSafe Jev 1.14":0.63,"Perplexity Decider":0.9062314749745906,"Liquid D1":0.939913356558485,"Mercury Decide":0.9796676489576609,"Cloudflare Clef":0.535,"cloudflare/clef-flash":0.5056,"cloudflare/clef-omni":0.1632,"liquid/d1-ultra":0.945994570109109,"open/intern-decision-4b":0.5313278281391198,"open/robojev-27b-v1@0.5":0.8968249851092878,"open/robojev-27b":null,"open/robojev-4b-v2":0.004905405551811006,"open/robojev-4b-v3@0.25":0.9525741338729858,"open/robojev-4b-v3@0.5":0.9035094985644659,"open/robojev-4b-v3@0.75":0.41165138407414853,"open/robojev-4b-v3":0.12384396710192513,"openai/gpt-6-luna-decisions":0.23,"perplexity/pplx-decider-flash-v1.2":0.695722169991145,"respan/span-02":0.21024701,"typesafe/jev-1.13":0.79,"JEV-27B-VL (10 frames)":0.6547305592403002,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.38671875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/617953b2-0c74-4499-93a5-b016311a1186","task":"Stack the green block on the red block","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"617953b2-0c74-4499-93a5-b016311a1186","predictions":{"RoboJev-27B":0.4376951115325321,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.89,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":0.6510474336657903,"TypeSafe Jev 1.14":0.59,"Perplexity Decider":0.795422704382098,"Liquid D1":0.28140560742914383,"Mercury Decide":0.9046505325302034,"Cloudflare Clef":0.2565,"cloudflare/clef-flash":0.1899,"cloudflare/clef-omni":0.1108,"liquid/d1-ultra":0.42648958363704076,"open/intern-decision-4b":0.4843206825122851,"open/robojev-27b-v1@0.5":0.8350284315865844,"open/robojev-27b":null,"open/robojev-4b-v2":0.0790476748344352,"open/robojev-4b-v3@0.25":0.5926666259765625,"open/robojev-4b-v3@0.5":0.1618215453479303,"open/robojev-4b-v3@0.75":0.14359896906129718,"open/robojev-4b-v3":0.12384396710192513,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3324593879017429,"respan/span-02":0.06910428,"typesafe/jev-1.13":0.57,"JEV-27B-VL (10 frames)":0.5337550049707825,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.04736328125}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/61f2c0c4-5388-436d-8933-4b7f9f2b04ce","task":"Put the eraser to the blue pencil box","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"61f2c0c4-5388-436d-8933-4b7f9f2b04ce","predictions":{"RoboJev-27B":0.013700870767569807,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.062302290353773306,"TypeSafe Jev 1.14":0.07,"Perplexity Decider":0.07667586856238072,"Liquid D1":0.34864513533394575,"Mercury Decide":0.06754668550840877,"Cloudflare Clef":0.2002,"cloudflare/clef-flash":0.2495,"cloudflare/clef-omni":0.1273,"liquid/d1-ultra":0.21695808790979368,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.006559744851461868,"open/robojev-27b":null,"open/robojev-4b-v2":0.02618406111961536,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.02450159025746704,"open/robojev-4b-v3@0.75":0.012071514031475902,"open/robojev-4b-v3":0.007064018099624773,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.22999140856681055,"respan/span-02":0.045552265,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.05652693160154535,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.07080078125}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/684df06a-c3f2-4148-86a8-c329ab37e8a2","task":"Press the button","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"684df06a-c3f2-4148-86a8-c329ab37e8a2","predictions":{"RoboJev-27B":0.06459831182868957,"GPT-6 Astra":0.05,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.08,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.028529605555505787,"TypeSafe Jev 1.14":0.11,"Perplexity Decider":0.057988870789137476,"Liquid D1":0.23370636225126956,"Mercury Decide":0.020332351376256382,"Cloudflare Clef":0.2801,"cloudflare/clef-flash":0.1649,"cloudflare/clef-omni":0.1352,"liquid/d1-ultra":0.11671091915814649,"open/intern-decision-4b":0.23289806532119295,"open/robojev-27b-v1@0.5":0.007482013313066811,"open/robojev-27b":null,"open/robojev-4b-v2":0.10500058508962046,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.102380250911392,"open/robojev-4b-v3@0.75":0.06792255924998467,"open/robojev-4b-v3":0.05887058738679302,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3291661427422473,"respan/span-02":0.0752507,"typesafe/jev-1.13":0.09,"JEV-27B-VL (10 frames)":0.046116477227736735,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00347900390625}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/68f344b6-cc5e-478a-ad41-12a973256256","task":"Put the red bowl on the blue plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"68f344b6-cc5e-478a-ad41-12a973256256","predictions":{"RoboJev-27B":0.0011507214883337339,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.0005431206481048166,"TypeSafe Jev 1.14":0.02,"Perplexity Decider":0.01380238554313188,"Liquid D1":0.060086652698692546,"Mercury Decide":0.0015011820124394362,"Cloudflare Clef":0.0545,"cloudflare/clef-flash":0.1481,"cloudflare/clef-omni":0.0455,"liquid/d1-ultra":0.062090641597065205,"open/intern-decision-4b":0.4069889545588398,"open/robojev-27b-v1@0.5":0.00013559994905880618,"open/robojev-27b":null,"open/robojev-4b-v2":0.005361080321059209,"open/robojev-4b-v3@0.25":0.02595735713839531,"open/robojev-4b-v3@0.5":0.008141294289513608,"open/robojev-4b-v3@0.75":0.005604465074944334,"open/robojev-4b-v3":0.0041144364846599805,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.010645663392862936,"respan/span-02":0.09426033,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.000378924188957817,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006103515625}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/6b4bdff6-ae9f-47d3-8887-9c57f3b5825f","task":"Collect the fork to the yellow box","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"6b4bdff6-ae9f-47d3-8887-9c57f3b5825f","predictions":{"RoboJev-27B":0.9119028082062706,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.8926292776646462,"TypeSafe Jev 1.14":0.59,"Perplexity Decider":0.941567330411326,"Liquid D1":0.9740426456278624,"Mercury Decide":0.9953904279317293,"Cloudflare Clef":0.5627,"cloudflare/clef-flash":0.5291,"cloudflare/clef-omni":0.4287,"liquid/d1-ultra":0.7382047509865145,"open/intern-decision-4b":0.608060011110835,"open/robojev-27b-v1@0.5":0.9589012047172499,"open/robojev-27b":null,"open/robojev-4b-v2":0.16086775395337108,"open/robojev-4b-v3@0.25":0.9465966820716858,"open/robojev-4b-v3@0.5":0.9565659184411002,"open/robojev-4b-v3@0.75":0.9541617453379198,"open/robojev-4b-v3":0.9118918620554844,"openai/gpt-6-luna-decisions":0.03,"perplexity/pplx-decider-flash-v1.2":0.8786737934367523,"respan/span-02":0.8244738,"typesafe/jev-1.13":0.85,"JEV-27B-VL (10 frames)":0.7712317809484227,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.208984375}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/74caa26d-a04f-44f3-9abb-a4827da25c55","task":"Put the red cup on the purple coaster","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"74caa26d-a04f-44f3-9abb-a4827da25c55","predictions":{"RoboJev-27B":0.9672441061551394,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":0.9416007082994379,"TypeSafe Jev 1.14":0.76,"Perplexity Decider":0.9796812909346632,"Liquid D1":0.9859363715104345,"Mercury Decide":0.9947798736293675,"Cloudflare Clef":0.734,"cloudflare/clef-flash":0.8528,"cloudflare/clef-omni":0.1128,"liquid/d1-ultra":0.9379093614872308,"open/intern-decision-4b":0.9156019658234928,"open/robojev-27b-v1@0.5":0.9796024400912398,"open/robojev-27b":null,"open/robojev-4b-v2":0.006996270681650968,"open/robojev-4b-v3@0.25":0.970687747001648,"open/robojev-4b-v3@0.5":0.975498409742533,"open/robojev-4b-v3@0.75":0.9693020651146849,"open/robojev-4b-v3":0.9684435763811455,"openai/gpt-6-luna-decisions":0.85,"perplexity/pplx-decider-flash-v1.2":0.9837511164367607,"respan/span-02":0.9375633,"typesafe/jev-1.13":0.88,"JEV-27B-VL (10 frames)":0.9396954047962534,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.92578125}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/750ba6b6-7c12-4b81-a69b-c0b815a920cf","task":"Put the red bowl on the blue plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"750ba6b6-7c12-4b81-a69b-c0b815a920cf","predictions":{"RoboJev-27B":0.9904686183476277,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":0.9780538964715292,"TypeSafe Jev 1.14":0.86,"Perplexity Decider":0.9896310947450332,"Liquid D1":0.9953904274702225,"Mercury Decide":0.9971990725295351,"Cloudflare Clef":0.9167,"cloudflare/clef-flash":0.8784,"cloudflare/clef-omni":0.0863,"liquid/d1-ultra":0.9349716833921934,"open/intern-decision-4b":0.8184242551251981,"open/robojev-27b-v1@0.5":0.994128201826613,"open/robojev-27b":null,"open/robojev-4b-v2":0.010890344798324344,"open/robojev-4b-v3@0.25":0.9859364032745361,"open/robojev-4b-v3@0.5":0.9833564251170067,"open/robojev-4b-v3@0.75":0.9613683489514899,"open/robojev-4b-v3":0.9411294126132068,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.9838146695257457,"respan/span-02":0.9697088,"typesafe/jev-1.13":0.92,"JEV-27B-VL (10 frames)":0.9678890092090883,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.921875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/791ea86c-fe1a-450f-833c-a0b045e6217a","task":"Put the bread in the oven","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"791ea86c-fe1a-450f-833c-a0b045e6217a","predictions":{"RoboJev-27B":0.0006961474308669857,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.01,"JEV-27B-VL":0.0002649058505636477,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.007646253907075195,"Liquid D1":0.009708474475791274,"Mercury Decide":0.0006263342420547713,"Cloudflare Clef":0.0862,"cloudflare/clef-flash":0.1599,"cloudflare/clef-omni":0.0963,"liquid/d1-ultra":0.008671445618095412,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.00011894564769011109,"open/robojev-27b":null,"open/robojev-4b-v2":0.003007688028932422,"open/robojev-4b-v3@0.25":0.01798621006309986,"open/robojev-4b-v3@0.5":0.006692850574775813,"open/robojev-4b-v3@0.75":0.006692850722353873,"open/robojev-4b-v3":0.005691671058411752,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.11470457848059193,"respan/span-02":0.057853702,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.0001227644101125263,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0012054443359375}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/86ff460f-e40b-491e-8c86-7a07b4a49e63","task":"Put the marker into the pen cup","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"86ff460f-e40b-491e-8c86-7a07b4a49e63","predictions":{"RoboJev-27B":0.01137398785584652,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.08529153157419593,"TypeSafe Jev 1.14":0.1,"Perplexity Decider":0.06265877058469087,"Liquid D1":0.06371499158516146,"Mercury Decide":0.03308597767364294,"Cloudflare Clef":0.2532,"cloudflare/clef-flash":0.2756,"cloudflare/clef-omni":0.0921,"liquid/d1-ultra":0.09357237981851461,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.0065463664490280305,"open/robojev-27b":null,"open/robojev-4b-v2":0.005361080321059209,"open/robojev-4b-v3@0.25":0.10669060051441193,"open/robojev-4b-v3@0.5":0.03372324040197287,"open/robojev-4b-v3@0.75":0.02297736967873775,"open/robojev-4b-v3":0.021788411170123766,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2006035556850079,"respan/span-02":0.06160749,"typesafe/jev-1.13":0.16,"JEV-27B-VL (10 frames)":0.0273540080211805,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01544189453125}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/88178ad3-413a-48e1-8256-86833dfce3d7","task":"Stack the green block on the red block","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"88178ad3-413a-48e1-8256-86833dfce3d7","predictions":{"RoboJev-27B":0.6015588725511634,"GPT-6 Astra":0.86,"GPT-6.1 Sol":0.86,"Claude Opus 5.5":0.45,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":0.3974365301113748,"TypeSafe Jev 1.14":0.6,"Perplexity Decider":0.38393044132795046,"Liquid D1":0.10087863083945883,"Mercury Decide":0.11920292045759123,"Cloudflare Clef":0.388,"cloudflare/clef-flash":0.2251,"cloudflare/clef-omni":0.17,"liquid/d1-ultra":0.42648958363704076,"open/intern-decision-4b":0.34810523633137336,"open/robojev-27b-v1@0.5":0.6320056597231112,"open/robojev-27b":null,"open/robojev-4b-v2":0.009538288429694562,"open/robojev-4b-v3@0.25":0.18242551386356354,"open/robojev-4b-v3@0.5":0.05577981318289087,"open/robojev-4b-v3@0.75":0.054313266183183405,"open/robojev-4b-v3":0.045499872888298876,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3358599172950286,"respan/span-02":0.15016605,"typesafe/jev-1.13":0.63,"JEV-27B-VL (10 frames)":0.6590126638568308,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.010986328125}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/8876fcd1-4268-4508-8814-4ff9030650e0","task":"Put the eraser to the blue pencil box","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"8876fcd1-4268-4508-8814-4ff9030650e0","predictions":{"RoboJev-27B":0.8117443282534598,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.68,"JEV-27B-VL":0.5345460039801715,"TypeSafe Jev 1.14":0.56,"Perplexity Decider":0.7996086310580262,"Liquid D1":0.9944450764281404,"Mercury Decide":0.7310585669110203,"Cloudflare Clef":0.6035,"cloudflare/clef-flash":0.6695,"cloudflare/clef-omni":0.1385,"liquid/d1-ultra":0.8360373742354359,"open/intern-decision-4b":0.8748864949022742,"open/robojev-27b-v1@0.5":0.6691267135117946,"open/robojev-27b":null,"open/robojev-4b-v2":0.033953688356658976,"open/robojev-4b-v3@0.25":0.957912266254425,"open/robojev-4b-v3@0.5":0.549182531250921,"open/robojev-4b-v3@0.75":0.09953688489563063,"open/robojev-4b-v3":0.038921036473713755,"openai/gpt-6-luna-decisions":0.94,"perplexity/pplx-decider-flash-v1.2":0.7056745133918241,"respan/span-02":0.8477574,"typesafe/jev-1.13":0.62,"JEV-27B-VL (10 frames)":0.6798862455502317,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.099609375}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/8b8341bf-0396-44fd-9484-f8d47af51e4d","task":"Press the button","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"8b8341bf-0396-44fd-9484-f8d47af51e4d","predictions":{"RoboJev-27B":0.18180496306190105,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.14532428272937806,"TypeSafe Jev 1.14":0.33,"Perplexity Decider":0.09560560690083549,"Liquid D1":0.1403362566809061,"Mercury Decide":0.13296422989056964,"Cloudflare Clef":0.2793,"cloudflare/clef-flash":0.1947,"cloudflare/clef-omni":0.1443,"liquid/d1-ultra":0.31220409188357706,"open/intern-decision-4b":0.30670018569615076,"open/robojev-27b-v1@0.5":0.03613102464505553,"open/robojev-27b":null,"open/robojev-4b-v2":0.16086775395337108,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.1368024864039654,"open/robojev-4b-v3@0.75":0.1050005837572588,"open/robojev-4b-v3":0.09257358731935178,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.3363161520487145,"respan/span-02":0.29349545,"typesafe/jev-1.13":0.17,"JEV-27B-VL (10 frames)":0.17620646452995165,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.004608154296875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/9335db6e-2f48-4c9c-9dac-4ffad1b21e47","task":"Put the apple in the yellow plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"9335db6e-2f48-4c9c-9dac-4ffad1b21e47","predictions":{"RoboJev-27B":0.00027664279166987057,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.011173786073019389,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.026919110558155154,"Liquid D1":0.09009299640503438,"Mercury Decide":0.003376612607394482,"Cloudflare Clef":0.054,"cloudflare/clef-flash":0.1069,"cloudflare/clef-omni":0.0628,"liquid/d1-ultra":0.029173328050461963,"open/intern-decision-4b":0.15526082656247686,"open/robojev-27b-v1@0.5":0.0015043421711009248,"open/robojev-27b":null,"open/robojev-4b-v2":0.0032876614041202805,"open/robojev-4b-v3@0.25":0.01243165135383606,"open/robojev-4b-v3@0.5":0.0055006754673125515,"open/robojev-4b-v3@0.75":0.0041678002213721265,"open/robojev-4b-v3":0.0023934843568307186,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.02472941046496125,"respan/span-02":0.027635826,"typesafe/jev-1.13":0.04,"JEV-27B-VL (10 frames)":0.0036900213440490544,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01031494140625}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/9499eb4c-a76d-4fc4-ab9b-82f5366b6aec","task":"Add pepper to the green bowl","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"9499eb4c-a76d-4fc4-ab9b-82f5366b6aec","predictions":{"RoboJev-27B":0.21071232163064982,"GPT-6 Astra":0.91,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.17200325280971474,"TypeSafe Jev 1.14":0.36,"Perplexity Decider":0.23556978431472378,"Liquid D1":0.24508500761839525,"Mercury Decide":0.03308597576681317,"Cloudflare Clef":0.2608,"cloudflare/clef-flash":0.4162,"cloudflare/clef-omni":0.1397,"liquid/d1-ultra":0.2617952535625818,"open/intern-decision-4b":0.4069889545588398,"open/robojev-27b-v1@0.5":0.021012021044936227,"open/robojev-27b":null,"open/robojev-4b-v2":0.006996270681650968,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.1709446101989739,"open/robojev-4b-v3@0.75":0.13643297762397494,"open/robojev-4b-v3":0.14264680034200217,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.20308759290593853,"respan/span-02":0.048841648,"typesafe/jev-1.13":0.38,"JEV-27B-VL (10 frames)":0.09569532088345731,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.03173828125}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/94ab3d4f-3866-46b1-be59-25ec344434ec","task":"Put the eraser to the blue pencil box","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"94ab3d4f-3866-46b1-be59-25ec344434ec","predictions":{"RoboJev-27B":0.5567408412808088,"GPT-6 Astra":0.87,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.609805492670407,"TypeSafe Jev 1.14":0.57,"Perplexity Decider":0.6014874956051424,"Liquid D1":0.33458944125318596,"Mercury Decide":0.37754066879814546,"Cloudflare Clef":0.3249,"cloudflare/clef-flash":0.3166,"cloudflare/clef-omni":0.1241,"liquid/d1-ultra":0.4386055069579756,"open/intern-decision-4b":0.5313278281391198,"open/robojev-27b-v1@0.5":0.7750490149788786,"open/robojev-27b":null,"open/robojev-4b-v2":0.0790476748344352,"open/robojev-4b-v3@0.25":0.8354835510253906,"open/robojev-4b-v3@0.5":0.8095931022908179,"open/robojev-4b-v3@0.75":0.7094794355493901,"open/robojev-4b-v3":0.20445237038006636,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.6125917138423301,"respan/span-02":0.39413217,"typesafe/jev-1.13":0.34,"JEV-27B-VL (10 frames)":0.38067248024239736,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.21875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/9fb9e17c-f83d-4054-9341-3408050a9eb0","task":"Put the red cup on the purple coaster","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"9fb9e17c-f83d-4054-9341-3408050a9eb0","predictions":{"RoboJev-27B":0.0033136195032458086,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.00022665793486322439,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.00667056127771128,"Liquid D1":0.00040448148127386445,"Mercury Decide":0.0004044814827800659,"Cloudflare Clef":0.0425,"cloudflare/clef-flash":0.1103,"cloudflare/clef-omni":0.1145,"liquid/d1-ultra":0.02525904945954693,"open/intern-decision-4b":0.10012611628383591,"open/robojev-27b-v1@0.5":0.0003930878372607072,"open/robojev-27b":null,"open/robojev-4b-v2":0.001842766452331557,"open/robojev-4b-v3@0.25":0.008577484637498856,"open/robojev-4b-v3@0.5":0.004825770646864498,"open/robojev-4b-v3@0.75":0.004978582695254881,"open/robojev-4b-v3":0.005108442412304043,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.07768705409326909,"respan/span-02":0.031694837,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.0032382973213583533,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0037078857421875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/a1d64fd0-f867-4ea6-b266-dda7421d46a5","task":"Put the red bowl on the blue plate","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"a1d64fd0-f867-4ea6-b266-dda7421d46a5","predictions":{"RoboJev-27B":0.000923476947137549,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.006277612264060087,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.010407145249553345,"Liquid D1":0.10669058684467357,"Mercury Decide":0.0029810331782752766,"Cloudflare Clef":0.0748,"cloudflare/clef-flash":0.1594,"cloudflare/clef-omni":0.0551,"liquid/d1-ultra":0.05927725034877882,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.00026353583351904775,"open/robojev-27b":null,"open/robojev-4b-v2":0.004488287139460313,"open/robojev-4b-v3@0.25":0.014063626527786255,"open/robojev-4b-v3@0.5":0.003477719953801495,"open/robojev-4b-v3@0.75":0.0023025600819802016,"open/robojev-4b-v3":0.0011822765498233803,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.08936065493358886,"respan/span-02":0.035264306,"typesafe/jev-1.13":0.05,"JEV-27B-VL (10 frames)":0.0008175253898600085,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.006683349609375}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/a4f3f876-bd3e-48e3-af86-d8a0b82dac1b","task":"Put the marker into the pen cup","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"a4f3f876-bd3e-48e3-af86-d8a0b82dac1b","predictions":{"RoboJev-27B":0.01626801485438731,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":0.023210185826924284,"TypeSafe Jev 1.14":0.07,"Perplexity Decider":0.05429778580319275,"Liquid D1":0.07585818211049715,"Mercury Decide":0.012431653528729221,"Cloudflare Clef":0.1458,"cloudflare/clef-flash":0.2612,"cloudflare/clef-omni":0.093,"liquid/d1-ultra":0.06809489549599611,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.0031445242759142625,"open/robojev-27b":null,"open/robojev-4b-v2":0.00731334505501762,"open/robojev-4b-v3@0.25":0.037326883524656296,"open/robojev-4b-v3@0.5":0.01203420913122135,"open/robojev-4b-v3@0.75":0.01011736424150334,"open/robojev-4b-v3":0.009249319533522623,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.07859326433552175,"respan/span-02":0.0940131,"typesafe/jev-1.13":0.09,"JEV-27B-VL (10 frames)":0.023606960381601722,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0012054443359375}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/aa8e896a-8c93-4e4d-82c1-7f360cf196f4","task":"Press the button","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"aa8e896a-8c93-4e4d-82c1-7f360cf196f4","predictions":{"RoboJev-27B":0.11852840277306056,"GPT-6 Astra":0.03,"GPT-6.1 Sol":null,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.41601955882442765,"TypeSafe Jev 1.14":0.23,"Perplexity Decider":0.2499777346073277,"Liquid D1":0.3775406547908327,"Mercury Decide":0.08509904848750824,"Cloudflare Clef":0.4478,"cloudflare/clef-flash":0.2634,"cloudflare/clef-omni":0.1544,"liquid/d1-ultra":0.25236786828046404,"open/intern-decision-4b":0.36247442200877295,"open/robojev-27b-v1@0.5":0.04880559996020898,"open/robojev-27b":null,"open/robojev-4b-v2":0.14917689162532846,"open/robojev-4b-v3@0.25":0.29421496391296387,"open/robojev-4b-v3@0.5":0.1709446101989739,"open/robojev-4b-v3@0.75":0.14359896906129718,"open/robojev-4b-v3":0.14264680034200217,"openai/gpt-6-luna-decisions":0.04,"perplexity/pplx-decider-flash-v1.2":0.2782313214122194,"respan/span-02":0.16786537,"typesafe/jev-1.13":0.19,"JEV-27B-VL (10 frames)":0.3170503978226717,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0028839111328125}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/b1915814-9211-4265-8cc7-22aee4b5069c","task":"Put the red bowl on the blue plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"b1915814-9211-4265-8cc7-22aee4b5069c","predictions":{"RoboJev-27B":0.9633287835902942,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.88,"JEV-27B-VL":0.9452979007742626,"TypeSafe Jev 1.14":0.75,"Perplexity Decider":0.9490670868543707,"Liquid D1":0.9989677688076688,"Mercury Decide":0.9980732652381701,"Cloudflare Clef":0.9148,"cloudflare/clef-flash":0.7867,"cloudflare/clef-omni":0.228,"liquid/d1-ultra":0.9182549624169375,"open/intern-decision-4b":0.9053865123447689,"open/robojev-27b-v1@0.5":0.9779781606421651,"open/robojev-27b":null,"open/robojev-4b-v2":0.03863165331656982,"open/robojev-4b-v3@0.25":0.9399133324623108,"open/robojev-4b-v3@0.5":0.32658221149990796,"open/robojev-4b-v3@0.75":0.2905205644506098,"open/robojev-4b-v3":0.2322495721973338,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.9596123912551414,"respan/span-02":0.9580393,"typesafe/jev-1.13":0.93,"JEV-27B-VL (10 frames)":0.9035874832059988,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/b6d12e9b-5c64-4c31-80eb-2545502fa66e","task":"Stack the green block on the red block","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"b6d12e9b-5c64-4c31-80eb-2545502fa66e","predictions":{"RoboJev-27B":0.027216762590024035,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.04454307180629802,"TypeSafe Jev 1.14":0.06,"Perplexity Decider":0.0695719567182093,"Liquid D1":0.08509904732734556,"Mercury Decide":0.029312228737436687,"Cloudflare Clef":0.1256,"cloudflare/clef-flash":0.1893,"cloudflare/clef-omni":0.1423,"liquid/d1-ultra":0.1218969741143165,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.0029309844585045227,"open/robojev-27b":null,"open/robojev-4b-v2":0.028559627850600573,"open/robojev-4b-v3@0.25":0.04742587357759476,"open/robojev-4b-v3@0.5":0.017755273617510888,"open/robojev-4b-v3@0.75":0.011381877728436919,"open/robojev-4b-v3":0.012102416042214261,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.09065357512904441,"respan/span-02":0.096287735,"typesafe/jev-1.13":0.09,"JEV-27B-VL (10 frames)":0.02404620059445072,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00186920166015625}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/b9855951-dc6f-42bf-b5c1-7a66500ce0cd","task":"Put the bread in the oven","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"b9855951-dc6f-42bf-b5c1-7a66500ce0cd","predictions":{"RoboJev-27B":0.0009203529102233022,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.01,"JEV-27B-VL":0.00016915471015763875,"TypeSafe Jev 1.14":0.03,"Perplexity Decider":0.005636691792469067,"Liquid D1":0.027585284425215593,"Mercury Decide":0.001410358396932915,"Cloudflare Clef":0.0667,"cloudflare/clef-flash":0.1802,"cloudflare/clef-omni":0.0694,"liquid/d1-ultra":0.02185813657924328,"open/intern-decision-4b":0.11201237577359563,"open/robojev-27b-v1@0.5":6.924974902904873e-06,"open/robojev-27b":null,"open/robojev-4b-v2":0.0022022489536237186,"open/robojev-4b-v3@0.25":0.022977370768785477,"open/robojev-4b-v3@0.5":0.011276606158891207,"open/robojev-4b-v3@0.75":0.008476838215708002,"open/robojev-4b-v3":0.010869457225645628,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.05606790845107634,"respan/span-02":0.13651596,"typesafe/jev-1.13":0.03,"JEV-27B-VL (10 frames)":7.14403569138822e-05,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00145721435546875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/bb94f08a-afac-42d8-9042-0f9396372547","task":"Add pepper to the green bowl","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"bb94f08a-afac-42d8-9042-0f9396372547","predictions":{"RoboJev-27B":0.023549152345378944,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":0.02136499204778088,"TypeSafe Jev 1.14":0.09,"Perplexity Decider":0.035169545431051226,"Liquid D1":0.037326888415033926,"Mercury Decide":0.01590639074964399,"Cloudflare Clef":0.1925,"cloudflare/clef-flash":0.2193,"cloudflare/clef-omni":0.1193,"liquid/d1-ultra":0.07811527233897028,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.001404212417848649,"open/robojev-27b":null,"open/robojev-4b-v2":0.002876746893908692,"open/robojev-4b-v3@0.25":0.02595735713839531,"open/robojev-4b-v3@0.5":0.007626874902958847,"open/robojev-4b-v3@0.75":0.005604465074944334,"open/robojev-4b-v3":0.004343237452522156,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.16789740631057573,"respan/span-02":0.04889759,"typesafe/jev-1.13":0.09,"JEV-27B-VL (10 frames)":0.02689962797294986,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0047607421875}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/d90b46c1-b89f-4113-b823-18d9d03c3e42","task":"Put the red cup on the purple coaster","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"d90b46c1-b89f-4113-b823-18d9d03c3e42","predictions":{"RoboJev-27B":0.9869023370240234,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.9696982146320271,"TypeSafe Jev 1.14":0.68,"Perplexity Decider":0.9791344966595639,"Liquid D1":0.9850429168097871,"Mercury Decide":0.9964063969050244,"Cloudflare Clef":0.6858,"cloudflare/clef-flash":0.8283,"cloudflare/clef-omni":0.2363,"liquid/d1-ultra":0.9530796189219665,"open/intern-decision-4b":0.9053865123447689,"open/robojev-27b-v1@0.5":0.9921731506617842,"open/robojev-27b":null,"open/robojev-4b-v2":0.7614624931929147,"open/robojev-4b-v3@0.25":0.970687747001648,"open/robojev-4b-v3@0.5":0.9537489247538957,"open/robojev-4b-v3@0.75":0.9004631151043695,"open/robojev-4b-v3":0.8042455501618967,"openai/gpt-6-luna-decisions":0.93,"perplexity/pplx-decider-flash-v1.2":0.9511227399731895,"respan/span-02":0.8188753,"typesafe/jev-1.13":0.81,"JEV-27B-VL (10 frames)":0.9389119809739537,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.8125}},{"suite":"unseen","id":"rbm-ood/utd_so101_clutter/dfa63bb1-a670-4844-978f-878a4bfef77f","task":"Put the apple in the yellow plate","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_clutter","episode":"dfa63bb1-a670-4844-978f-878a4bfef77f","predictions":{"RoboJev-27B":0.9209784858833798,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.7,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":0.9551077382017339,"TypeSafe Jev 1.14":0.84,"Perplexity Decider":0.9132825853604558,"Liquid D1":0.9993736658675405,"Mercury Decide":0.974042642048694,"Cloudflare Clef":0.8267,"cloudflare/clef-flash":0.8624,"cloudflare/clef-omni":0.3214,"liquid/d1-ultra":0.8220509985385663,"open/intern-decision-4b":0.8879876242264044,"open/robojev-27b-v1@0.5":0.9271503135072879,"open/robojev-27b":null,"open/robojev-4b-v2":0.6097897641298211,"open/robojev-4b-v3@0.25":0.9796676635742188,"open/robojev-4b-v3@0.5":0.8780062831580779,"open/robojev-4b-v3@0.75":0.4851234373721735,"open/robojev-4b-v3":0.2841612815794545,"openai/gpt-6-luna-decisions":0.96,"perplexity/pplx-decider-flash-v1.2":0.8858999293844884,"respan/span-02":0.97168845,"typesafe/jev-1.13":0.92,"JEV-27B-VL (10 frames)":0.929078196748246,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2109375}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/1bf2b88d-7f02-421e-8397-131eda348b22","task":"Press the button.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"1bf2b88d-7f02-421e-8397-131eda348b22","predictions":{"RoboJev-27B":0.9168222251171351,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":0.7236312201939816,"TypeSafe Jev 1.14":0.73,"Perplexity Decider":0.7230320612904827,"Liquid D1":0.9465966660571644,"Mercury Decide":0.9149009631141181,"Cloudflare Clef":0.7911,"cloudflare/clef-flash":0.468,"cloudflare/clef-omni":0.4694,"liquid/d1-ultra":0.8491262170961453,"open/intern-decision-4b":0.5777854893190272,"open/robojev-27b-v1@0.5":0.9361772780967573,"open/robojev-27b":null,"open/robojev-4b-v2":0.7694764153481521,"open/robojev-4b-v3@0.25":0.9241418242454529,"open/robojev-4b-v3@0.5":0.9328665051276483,"open/robojev-4b-v3@0.75":0.9320774407500154,"open/robojev-4b-v3":0.9118918620554844,"openai/gpt-6-luna-decisions":0.77,"perplexity/pplx-decider-flash-v1.2":0.6579695145678044,"respan/span-02":0.32286614,"typesafe/jev-1.13":0.75,"JEV-27B-VL (10 frames)":0.8514018871365602,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1474609375}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/21729a47-ac6e-481b-9a33-fc2de1b007b8","task":"Collect the fork to the yellow box.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"21729a47-ac6e-481b-9a33-fc2de1b007b8","predictions":{"RoboJev-27B":0.26778371316632515,"GPT-6 Astra":0.86,"GPT-6.1 Sol":0.85,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.35,"JEV-27B-VL":0.0766991735088283,"TypeSafe Jev 1.14":0.13,"Perplexity Decider":0.2181180065416645,"Liquid D1":0.2689414213699951,"Mercury Decide":0.029312229585402833,"Cloudflare Clef":0.2149,"cloudflare/clef-flash":0.2648,"cloudflare/clef-omni":0.2024,"liquid/d1-ultra":0.25236786828046404,"open/intern-decision-4b":0.34810523633137336,"open/robojev-27b-v1@0.5":0.03599357063164542,"open/robojev-27b":null,"open/robojev-4b-v2":0.03544887275269872,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.03593407330933149,"open/robojev-4b-v3@0.75":0.016188346495106164,"open/robojev-4b-v3":0.01958823717659324,"openai/gpt-6-luna-decisions":0.05,"perplexity/pplx-decider-flash-v1.2":0.1682014700611625,"respan/span-02":0.24873514,"typesafe/jev-1.13":0.22,"JEV-27B-VL (10 frames)":0.36454231062148407,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.111328125}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/2f215efc-41f5-45d7-b9b8-419a9cb7636d","task":"Put the eraser to the blue pencil box.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"2f215efc-41f5-45d7-b9b8-419a9cb7636d","predictions":{"RoboJev-27B":0.013725308945197173,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.07,"JEV-27B-VL":0.01609153332827998,"TypeSafe Jev 1.14":0.42,"Perplexity Decider":0.03645666328084699,"Liquid D1":0.24508500761839525,"Mercury Decide":0.0075772412258405045,"Cloudflare Clef":0.2025,"cloudflare/clef-flash":0.3075,"cloudflare/clef-omni":0.1144,"liquid/d1-ultra":0.21695809590771967,"open/intern-decision-4b":0.5,"open/robojev-27b-v1@0.5":0.0053080591426160175,"open/robojev-27b":null,"open/robojev-4b-v2":0.2551315027042466,"open/robojev-4b-v3@0.25":0.562176525592804,"open/robojev-4b-v3@0.5":0.4025775341117646,"open/robojev-4b-v3@0.75":0.2551315034592856,"open/robojev-4b-v3":0.2322495721973338,"openai/gpt-6-luna-decisions":0.23,"perplexity/pplx-decider-flash-v1.2":0.5445592046184614,"respan/span-02":0.45570612,"typesafe/jev-1.13":0.39,"JEV-27B-VL (10 frames)":0.03218066281511238,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0179443359375}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/445ee030-6595-43d7-b423-920160badd95","task":"Put the marker into the pen cup.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"445ee030-6595-43d7-b423-920160badd95","predictions":{"RoboJev-27B":0.10858983628223888,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.8,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.09022323717662534,"TypeSafe Jev 1.14":0.42,"Perplexity Decider":0.13437246062059352,"Liquid D1":0.6224593312018546,"Mercury Decide":0.017986211475461908,"Cloudflare Clef":0.3132,"cloudflare/clef-flash":0.2702,"cloudflare/clef-omni":0.2137,"liquid/d1-ultra":0.5369560013004135,"open/intern-decision-4b":0.22187782400103293,"open/robojev-27b-v1@0.5":0.030907087500736483,"open/robojev-27b":null,"open/robojev-4b-v2":0.016188347137528064,"open/robojev-4b-v3@0.25":0.16451644897460938,"open/robojev-4b-v3@0.5":0.11512034374911738,"open/robojev-4b-v3@0.75":0.1669856712343507,"open/robojev-4b-v3":0.2625786543234272,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.10450592400049198,"respan/span-02":0.14075395,"typesafe/jev-1.13":0.32,"JEV-27B-VL (10 frames)":0.17391831224168547,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.003173828125}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/512c763c-53b6-4c2b-86e9-366466033b92","task":"Put the pear in the yellow plate.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"512c763c-53b6-4c2b-86e9-366466033b92","predictions":{"RoboJev-27B":0.2598771124322046,"GPT-6 Astra":0.77,"GPT-6.1 Sol":0.72,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.35,"JEV-27B-VL":0.3315592681898058,"TypeSafe Jev 1.14":0.53,"Perplexity Decider":0.32695836082335555,"Liquid D1":0.8438951143326726,"Mercury Decide":0.26894141551050293,"Cloudflare Clef":0.3694,"cloudflare/clef-flash":0.1957,"cloudflare/clef-omni":0.0845,"liquid/d1-ultra":0.5123386675987678,"open/intern-decision-4b":0.34810523633137336,"open/robojev-27b-v1@0.5":0.09741504014159046,"open/robojev-27b":null,"open/robojev-4b-v2":0.3385768147857754,"open/robojev-4b-v3@0.25":0.4073334336280823,"open/robojev-4b-v3@0.5":0.1618215453479303,"open/robojev-4b-v3@0.75":0.09953688489563063,"open/robojev-4b-v3":0.06858087544025289,"openai/gpt-6-luna-decisions":0.08,"perplexity/pplx-decider-flash-v1.2":0.41372787886591955,"respan/span-02":0.09865651,"typesafe/jev-1.13":0.37,"JEV-27B-VL (10 frames)":0.23339691545689414,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.36328125}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/5549ead7-3ed8-4128-b0b5-c1931323a60e","task":"Add pepper to the green bowl.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"5549ead7-3ed8-4128-b0b5-c1931323a60e","predictions":{"RoboJev-27B":0.1619333512073928,"GPT-6 Astra":0.43,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.12893648103825725,"TypeSafe Jev 1.14":0.21,"Perplexity Decider":0.1307374605124606,"Liquid D1":0.4378235137849365,"Mercury Decide":0.022977369742764476,"Cloudflare Clef":0.2179,"cloudflare/clef-flash":0.224,"cloudflare/clef-omni":0.1793,"liquid/d1-ultra":0.2714469192385764,"open/intern-decision-4b":0.1724380672551571,"open/robojev-27b-v1@0.5":0.029580285808618757,"open/robojev-27b":null,"open/robojev-4b-v2":0.2385375068070853,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.03372324040197287,"open/robojev-4b-v3@0.75":0.02297736967873775,"open/robojev-4b-v3":0.021788411170123766,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.21197033979821228,"respan/span-02":0.074579075,"typesafe/jev-1.13":0.25,"JEV-27B-VL (10 frames)":0.1775922576372088,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01361083984375}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/64b4a773-12a2-4497-814f-27a5da09684c","task":"Stack the green block on the red block.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"64b4a773-12a2-4497-814f-27a5da09684c","predictions":{"RoboJev-27B":0.01765768161338096,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":9.678315408510287e-05,"TypeSafe Jev 1.14":0.05,"Perplexity Decider":0.017376747348403842,"Liquid D1":0.005220125964387991,"Mercury Decide":0.0006263342099923095,"Cloudflare Clef":0.0387,"cloudflare/clef-flash":0.1109,"cloudflare/clef-omni":0.0731,"liquid/d1-ultra":0.05400543440055178,"open/intern-decision-4b":0.13214384255458153,"open/robojev-27b-v1@0.5":0.00012804315224040205,"open/robojev-27b":null,"open/robojev-4b-v2":0.0009872071971691605,"open/robojev-4b-v3@0.25":0.014063626527786255,"open/robojev-4b-v3@0.5":0.006269376036423619,"open/robojev-4b-v3@0.75":0.012071514031475902,"open/robojev-4b-v3":0.017606235547797083,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.016179644410405904,"respan/span-02":0.0692722,"typesafe/jev-1.13":0.06,"JEV-27B-VL (10 frames)":0.05742300514168415,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01165771484375}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/6d82d9e7-e4b8-4e2b-ade6-e48192b4638a","task":"Put the red bowl on the blue plate.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"6d82d9e7-e4b8-4e2b-ade6-e48192b4638a","predictions":{"RoboJev-27B":0.008557064117262923,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.07,"JEV-27B-VL":0.0047373629239919925,"TypeSafe Jev 1.14":0.07,"Perplexity Decider":0.028517480994022366,"Liquid D1":0.01590639171181471,"Mercury Decide":0.007577240014255115,"Cloudflare Clef":0.099,"cloudflare/clef-flash":0.1143,"cloudflare/clef-omni":0.0437,"liquid/d1-ultra":0.06809489661629534,"open/intern-decision-4b":0.12511350509772579,"open/robojev-27b-v1@0.5":0.0011361089844618226,"open/robojev-27b":null,"open/robojev-4b-v2":0.009538288429694562,"open/robojev-4b-v3@0.25":0.020332353189587593,"open/robojev-4b-v3@0.5":0.011276606158891207,"open/robojev-4b-v3@0.75":0.012071514031475902,"open/robojev-4b-v3":0.01146957225399579,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.05758667955384592,"respan/span-02":0.0925855,"typesafe/jev-1.13":0.08,"JEV-27B-VL (10 frames)":0.013044564199444029,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0260009765625}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/6d954f3e-b9a3-4271-a9ea-d7636b9be07e","task":"Put the eraser to the blue pencil box.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"6d954f3e-b9a3-4271-a9ea-d7636b9be07e","predictions":{"RoboJev-27B":0.7006750743159834,"GPT-6 Astra":0.77,"GPT-6.1 Sol":0.84,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":0.6061339568260653,"TypeSafe Jev 1.14":0.64,"Perplexity Decider":0.5368234755354664,"Liquid D1":0.9740426450627306,"Mercury Decide":0.7772998611746911,"Cloudflare Clef":0.51,"cloudflare/clef-flash":0.7555,"cloudflare/clef-omni":0.5757,"liquid/d1-ultra":0.6439101958177847,"open/intern-decision-4b":0.7193152314525416,"open/robojev-27b-v1@0.5":0.4830547076110047,"open/robojev-27b":null,"open/robojev-4b-v2":0.4776933853656969,"open/robojev-4b-v3@0.25":0.9669140577316284,"open/robojev-4b-v3@0.5":0.972148766331303,"open/robojev-4b-v3@0.75":0.9693020651146849,"open/robojev-4b-v3":0.9684435763811455,"openai/gpt-6-luna-decisions":0.86,"perplexity/pplx-decider-flash-v1.2":0.7623653288396043,"respan/span-02":0.24267995,"typesafe/jev-1.13":0.75,"JEV-27B-VL (10 frames)":0.5575879586069475,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.5859375}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/75b851a5-9526-4603-9b3e-dfc71686e614","task":"Put the bread in the oven.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"75b851a5-9526-4603-9b3e-dfc71686e614","predictions":{"RoboJev-27B":0.05248791475731223,"GPT-6 Astra":0.38,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.17531905111490786,"TypeSafe Jev 1.14":0.13,"Perplexity Decider":0.19114462974570587,"Liquid D1":0.19193279569159502,"Mercury Decide":0.06008665017400762,"Cloudflare Clef":0.2189,"cloudflare/clef-flash":0.1139,"cloudflare/clef-omni":0.0748,"liquid/d1-ultra":0.20065406774920336,"open/intern-decision-4b":0.11201237577359563,"open/robojev-27b-v1@0.5":0.046222606314094306,"open/robojev-27b":null,"open/robojev-4b-v2":0.06161735137356937,"open/robojev-4b-v3@0.25":0.08509904146194458,"open/robojev-4b-v3@0.5":0.102380250911392,"open/robojev-4b-v3@0.75":0.14359896906129718,"open/robojev-4b-v3":0.21343419258585974,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.1690970680725525,"respan/span-02":0.05762789,"typesafe/jev-1.13":0.11,"JEV-27B-VL (10 frames)":0.0691898543469287,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.00628662109375}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/7a0167d6-f3ad-40d8-a7a8-73690f714994","task":"Add pepper to the green bowl.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"7a0167d6-f3ad-40d8-a7a8-73690f714994","predictions":{"RoboJev-27B":0.19671259138171235,"GPT-6 Astra":0.18,"GPT-6.1 Sol":0.18,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.1938550270197048,"TypeSafe Jev 1.14":0.26,"Perplexity Decider":0.19955709995828935,"Liquid D1":0.5312093733737563,"Mercury Decide":0.09534946040040723,"Cloudflare Clef":0.3337,"cloudflare/clef-flash":0.1795,"cloudflare/clef-omni":0.122,"liquid/d1-ultra":0.42648958363704076,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.0789581143389725,"open/robojev-27b":null,"open/robojev-4b-v2":0.10927050321483402,"open/robojev-4b-v3@0.25":0.24508501589298248,"open/robojev-4b-v3@0.5":0.2007555371763571,"open/robojev-4b-v3@0.75":0.23317378360550628,"open/robojev-4b-v3":0.19575444983810342,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2764846387012968,"respan/span-02":0.3436213,"typesafe/jev-1.13":0.34,"JEV-27B-VL (10 frames)":0.18126757161555473,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.01031494140625}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/7d6b7ad0-8503-4b28-9106-d51ca61a4774","task":"Put the red bowl on the blue plate.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"7d6b7ad0-8503-4b28-9106-d51ca61a4774","predictions":{"RoboJev-27B":0.8800341098518767,"GPT-6 Astra":0.89,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":0.523031441758764,"TypeSafe Jev 1.14":0.63,"Perplexity Decider":0.48840420782142385,"Liquid D1":0.9579122708828604,"Mercury Decide":0.20181322226037882,"Cloudflare Clef":0.2422,"cloudflare/clef-flash":0.4908,"cloudflare/clef-omni":0.266,"liquid/d1-ultra":0.698296662271134,"open/intern-decision-4b":0.37709365395745764,"open/robojev-27b-v1@0.5":0.13650180912934773,"open/robojev-27b":null,"open/robojev-4b-v2":0.05206535942424779,"open/robojev-4b-v3@0.25":0.3486451506614685,"open/robojev-4b-v3@0.5":0.102380250911392,"open/robojev-4b-v3@0.75":0.054313266183183405,"open/robojev-4b-v3":0.0299371453325719,"openai/gpt-6-luna-decisions":0.01,"perplexity/pplx-decider-flash-v1.2":0.5165668856397434,"respan/span-02":0.12192773,"typesafe/jev-1.13":0.61,"JEV-27B-VL (10 frames)":0.8270953286493448,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.119140625}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/a1fc1fc8-c2d5-4c4a-98c5-8649d595bc38","task":"Put the bread in the oven.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"a1fc1fc8-c2d5-4c4a-98c5-8649d595bc38","predictions":{"RoboJev-27B":0.45140174965093194,"GPT-6 Astra":0.65,"GPT-6.1 Sol":0.63,"Claude Opus 5.5":0.25,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.44623389740906944,"TypeSafe Jev 1.14":0.4,"Perplexity Decider":0.37772760057723237,"Liquid D1":0.8933094103149354,"Mercury Decide":0.22270014914315833,"Cloudflare Clef":0.2877,"cloudflare/clef-flash":0.3496,"cloudflare/clef-omni":0.4507,"liquid/d1-ultra":0.46304399869958657,"open/intern-decision-4b":0.37709365395745764,"open/robojev-27b-v1@0.5":0.1471578716377777,"open/robojev-27b":null,"open/robojev-4b-v2":0.09306389901723976,"open/robojev-4b-v3@0.25":0.8933094143867493,"open/robojev-4b-v3@0.5":0.8707824477141304,"open/robojev-4b-v3@0.75":0.7333927218765676,"open/robojev-4b-v3":0.3067798159797107,"openai/gpt-6-luna-decisions":0.02,"perplexity/pplx-decider-flash-v1.2":0.4844208141695367,"respan/span-02":0.20815533,"typesafe/jev-1.13":0.38,"JEV-27B-VL (10 frames)":0.4984146239187556,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.2158203125}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/a2abb33e-62d7-46a3-b9fc-0e5fae8e9374","task":"Put the pear in the yellow plate.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"a2abb33e-62d7-46a3-b9fc-0e5fae8e9374","predictions":{"RoboJev-27B":0.043686627924703014,"GPT-6 Astra":0.18,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.2394724120357783,"TypeSafe Jev 1.14":0.24,"Perplexity Decider":0.26148310839860744,"Liquid D1":0.3629691917376782,"Mercury Decide":0.07585817218654307,"Cloudflare Clef":0.3125,"cloudflare/clef-flash":0.1988,"cloudflare/clef-omni":0.1506,"liquid/d1-ultra":0.3122040716652746,"open/intern-decision-4b":0.25606104458540857,"open/robojev-27b-v1@0.5":0.08124651193335694,"open/robojev-27b":null,"open/robojev-4b-v2":0.31887895250001214,"open/robojev-4b-v3@0.25":0.2018132209777832,"open/robojev-4b-v3@0.5":0.21151967170194583,"open/robojev-4b-v3@0.75":0.15886909401879357,"open/robojev-4b-v3":0.08383818708105521,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.21570838206615792,"respan/span-02":0.13342668,"typesafe/jev-1.13":0.12,"JEV-27B-VL (10 frames)":0.36850568856755994,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0113525390625}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/c4657daa-d553-426c-b958-47091ad4a56b","task":"Press the button.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"c4657daa-d553-426c-b958-47091ad4a56b","predictions":{"RoboJev-27B":0.21272498422246067,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":0.23528944636627316,"TypeSafe Jev 1.14":0.22,"Perplexity Decider":0.16595197405581383,"Liquid D1":0.23370635691404026,"Mercury Decide":0.09534946361376598,"Cloudflare Clef":0.3926,"cloudflare/clef-flash":0.1962,"cloudflare/clef-omni":0.13,"liquid/d1-ultra":0.47533768343489957,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.06797559595464524,"open/robojev-27b":null,"open/robojev-4b-v2":0.21506799585334685,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.1368024864039654,"open/robojev-4b-v3@0.75":0.09432751595727837,"open/robojev-4b-v3":0.08810813794451551,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.23276814662626,"respan/span-02":0.10333912,"typesafe/jev-1.13":0.26,"JEV-27B-VL (10 frames)":0.3441554206662106,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0634765625}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/c83d87e4-f513-49c0-a445-236f5f8178da","task":"Put the red cup on the purple coaster.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"c83d87e4-f513-49c0-a445-236f5f8178da","predictions":{"RoboJev-27B":0.5301450022106282,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.45,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.04520328751020443,"TypeSafe Jev 1.14":0.13,"Perplexity Decider":0.1269397728600266,"Liquid D1":0.256831980010821,"Mercury Decide":0.029312233083263427,"Cloudflare Clef":0.1904,"cloudflare/clef-flash":0.131,"cloudflare/clef-omni":0.0405,"liquid/d1-ultra":0.20868887369264372,"open/intern-decision-4b":0.1636682776269396,"open/robojev-27b-v1@0.5":0.00905893505319167,"open/robojev-27b":null,"open/robojev-4b-v2":0.042087729958985645,"open/robojev-4b-v3@0.25":0.01798621006309986,"open/robojev-4b-v3@0.5":0.008141294289513608,"open/robojev-4b-v3@0.75":0.007990902377034759,"open/robojev-4b-v3":0.007064018099624773,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.0907369432409338,"respan/span-02":0.06804054,"typesafe/jev-1.13":0.25,"JEV-27B-VL (10 frames)":0.5177985618955936,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.1083984375}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/cafc691b-29da-42c7-a698-9fa089be70e4","task":"Stack the green block on the red block.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"cafc691b-29da-42c7-a698-9fa089be70e4","predictions":{"RoboJev-27B":0.7300989856333152,"GPT-6 Astra":0.85,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.62,"Claude Sonnet 5.5":0.45,"JEV-27B-VL":0.5669315681927458,"TypeSafe Jev 1.14":0.28,"Perplexity Decider":0.40556230785162883,"Liquid D1":0.32082130082460697,"Mercury Decide":0.29421496597446145,"Cloudflare Clef":0.3081,"cloudflare/clef-flash":0.1215,"cloudflare/clef-omni":0.1319,"liquid/d1-ultra":0.414461257641393,"open/intern-decision-4b":0.20097168954465905,"open/robojev-27b-v1@0.5":0.6895085906302284,"open/robojev-27b":null,"open/robojev-4b-v2":0.8391322460466288,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.11512034374911738,"open/robojev-4b-v3@0.75":0.09432751595727837,"open/robojev-4b-v3":0.07585818271507015,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.3657625912567975,"respan/span-02":0.7288275,"typesafe/jev-1.13":0.39,"JEV-27B-VL (10 frames)":0.658385013888581,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.21875}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/db2f87b5-131f-4b9f-974c-35a8c4bb72cf","task":"Put the marker into the pen cup.","label":"success","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"db2f87b5-131f-4b9f-974c-35a8c4bb72cf","predictions":{"RoboJev-27B":0.09615297937788587,"GPT-6 Astra":0.15,"GPT-6.1 Sol":0.73,"Claude Opus 5.5":0.45,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":0.1809569073999524,"TypeSafe Jev 1.14":0.33,"Perplexity Decider":0.1486384150990926,"Liquid D1":0.4073334000459302,"Mercury Decide":0.01798620739594212,"Cloudflare Clef":0.2131,"cloudflare/clef-flash":0.1553,"cloudflare/clef-omni":0.1132,"liquid/d1-ultra":0.20868888924130843,"open/intern-decision-4b":0.2681939143399331,"open/robojev-27b-v1@0.5":0.04902392655760186,"open/robojev-27b":null,"open/robojev-4b-v2":0.08579678054051716,"open/robojev-4b-v3@0.25":0.10669060051441193,"open/robojev-4b-v3@0.5":0.1368024864039654,"open/robojev-4b-v3@0.75":0.1295704729794557,"open/robojev-4b-v3":0.13612834674424493,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2596334734712773,"respan/span-02":0.09061455,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.19361843100525367,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.005218505859375}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/df6c7c10-ea07-4689-9a7f-df70144aaf8d","task":"Put the red cup on the purple coaster.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"df6c7c10-ea07-4689-9a7f-df70144aaf8d","predictions":{"RoboJev-27B":0.169450362247843,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":0.13875488695089483,"TypeSafe Jev 1.14":0.27,"Perplexity Decider":0.13084371004952552,"Liquid D1":0.6224593312018546,"Mercury Decide":0.03308597922294221,"Cloudflare Clef":0.275,"cloudflare/clef-flash":0.1893,"cloudflare/clef-omni":0.1691,"liquid/d1-ultra":0.25236786828046404,"open/intern-decision-4b":0.18157574487480185,"open/robojev-27b-v1@0.5":0.009454660986525447,"open/robojev-27b":null,"open/robojev-4b-v2":0.002876746893908692,"open/robojev-4b-v3@0.25":0.10669060051441193,"open/robojev-4b-v3@0.5":0.04924136119799765,"open/robojev-4b-v3@0.75":0.02167836395087896,"open/robojev-4b-v3":0.01146957225399579,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.48891416105262464,"respan/span-02":0.10538898,"typesafe/jev-1.13":0.28,"JEV-27B-VL (10 frames)":0.26278655909753385,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.0169677734375}},{"suite":"unseen","id":"rbm-ood/utd_so101_wrist/f954d318-fa05-449c-9e5b-aa8667de41ff","task":"Collect the fork to the yellow box.","label":"failure","scored":true,"source":"robometer/rbm-1m-ood","group":"utd_so101_wrist","episode":"f954d318-fa05-449c-9e5b-aa8667de41ff","predictions":{"RoboJev-27B":0.03765078872014275,"GPT-6 Astra":0.15,"GPT-6.1 Sol":0.66,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":0.11260139466562527,"TypeSafe Jev 1.14":0.23,"Perplexity Decider":0.2217065071931585,"Liquid D1":0.16451645880021026,"Mercury Decide":0.04208772566276722,"Cloudflare Clef":0.2291,"cloudflare/clef-flash":0.1507,"cloudflare/clef-omni":0.1548,"liquid/d1-ultra":0.2813188325544226,"open/intern-decision-4b":0.24429381869718142,"open/robojev-27b-v1@0.5":0.028130114853991025,"open/robojev-27b":null,"open/robojev-4b-v2":0.005604465165684275,"open/robojev-4b-v3@0.25":0.14804719388484955,"open/robojev-4b-v3@0.5":0.153095448827493,"open/robojev-4b-v3@0.75":0.09953688489563063,"open/robojev-4b-v3":0.053129261209546814,"openai/gpt-6-luna-decisions":0.0,"perplexity/pplx-decider-flash-v1.2":0.2508764012167242,"respan/span-02":0.21029522,"typesafe/jev-1.13":0.2,"JEV-27B-VL (10 frames)":0.08475676762224726,"open/robojev-27b (10 frames)":null,"open/robometer-4b":0.010009765625}},{"suite":"community","id":"1ys1/eval_n3_areumii-pickplace-v3/21","task":"Pick red cube and place it on blue basket","label":"failure","scored":true,"source":"1ys1/eval_n3_areumii-pickplace-v3","group":"areumii_c1","episode":"21","predictions":{"RoboJev-27B":0.00558326293346599,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"1ys1/eval_addcube_areumii-pickplace-v9/16","task":"Pick up the red cube and place it in the blue basket.","label":"failure","scored":true,"source":"1ys1/eval_addcube_areumii-pickplace-v9","group":"areumii_c1","episode":"16","predictions":{"RoboJev-27B":0.1422878653878783,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"ATR5607/eval_direct_real_100_v2/10","task":"Grab the Cylinder","label":"unclear","scored":false,"source":"ATR5607/eval_direct_real_100_v2","group":"koch_follower","episode":"10","predictions":{"RoboJev-27B":0.6987331598358223,"GPT-6 Astra":0.13,"GPT-6.1 Sol":0.18,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_ACT_S1_I_18_03_2026/9","task":"Place the cube in the bowl.","label":"success","scored":true,"source":"Alkatt/eval_ACT_S1_I_18_03_2026","group":"so_follower","episode":"9","predictions":{"RoboJev-27B":0.984329628388792,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LAVLA_Async_pickplace_run1_2026_07_28/9","task":"Pick up the red cube and place it in the red bowl","label":"success","scored":true,"source":"Alkatt/eval_LAVLA_Async_pickplace_run1_2026_07_28","group":"so_follower","episode":"9","predictions":{"RoboJev-27B":0.9891363129672516,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LAVLA_Sync_IV_redblue_cube_23_04_2026_full/0","task":"Place the red cube in the red bowl.","label":"failure","scored":true,"source":"Alkatt/eval_LAVLA_Sync_IV_redblue_cube_23_04_2026_full","group":"so_follower","episode":"0","predictions":{"RoboJev-27B":0.008093742465073765,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LAVLA_Sync_IV_redblue_cube_23_04_2026_v1/2","task":"Place the red cube in the red bowl.","label":"failure","scored":true,"source":"Alkatt/eval_LAVLA_Sync_IV_redblue_cube_23_04_2026_v1","group":"so_follower","episode":"2","predictions":{"RoboJev-27B":0.00856177939659842,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LDVLA_Async_pick_V3_run2_2026_09_14/8","task":"Pick up the red cube and place it in the red bowl","label":"failure","scored":true,"source":"Alkatt/eval_LDVLA_Async_pick_V3_run2_2026_09_14","group":"so_follower","episode":"8","predictions":{"RoboJev-27B":0.012951235824873071,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LAVLA_Sync_stack_run1_2026_07_27/36","task":"Pick up the red cube and put it on top of the blue cube","label":"success","scored":true,"source":"Alkatt/eval_LAVLA_Sync_stack_run1_2026_07_27","group":"so_follower","episode":"36","predictions":{"RoboJev-27B":0.9321483242701251,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LAVLA_Sync_pickplace_run3_2026_08_05/49","task":"Pick up the red cube and place it in the red bowl","label":"success","scored":true,"source":"Alkatt/eval_LAVLA_Sync_pickplace_run3_2026_08_05","group":"so_follower","episode":"49","predictions":{"RoboJev-27B":0.9893834134337958,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.92,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LDVLA_Sync_pick_V3_run5_2026_09_07/3","task":"Pick up the red cube and place it in the red bowl","label":"success","scored":true,"source":"Alkatt/eval_LDVLA_Sync_pick_V3_run5_2026_09_07","group":"so_follower","episode":"3","predictions":{"RoboJev-27B":0.9870624859628697,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LDVLA_Sync_pick_V3_run3_2026_09_07/22","task":"Pick up the red cube and place it in the red bowl","label":"success","scored":true,"source":"Alkatt/eval_LDVLA_Sync_pick_V3_run3_2026_09_07","group":"so_follower","episode":"22","predictions":{"RoboJev-27B":0.9880831487992645,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.92,"Claude Sonnet 5.5":0.95,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LDVLA_Async_sort_V3_run6_2026_09_16/45","task":"Put the red cube in the red bowl and the blue cube in the blue bowl","label":"failure","scored":true,"source":"Alkatt/eval_LDVLA_Async_sort_V3_run6_2026_09_16","group":"so_follower","episode":"45","predictions":{"RoboJev-27B":0.019894300639416135,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LDVLA_Sync_stack_V3_run1_2026_09_09/39","task":"Pick up the red cube and put it on top of the blue cube","label":"failure","scored":true,"source":"Alkatt/eval_LDVLA_Sync_stack_V3_run1_2026_09_09","group":"so_follower","episode":"39","predictions":{"RoboJev-27B":0.1317881308003873,"GPT-6 Astra":0.55,"GPT-6.1 Sol":0.8,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LDVLA_bfloat16_Async_stack_V3_run2_2026_10_20/48","task":"Pick up the red cube and put it on top of the blue cube","label":"failure","scored":true,"source":"Alkatt/eval_LDVLA_bfloat16_Async_stack_V3_run2_2026_10_20","group":"so_follower","episode":"48","predictions":{"RoboJev-27B":0.009540636452612179,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LDVLA_Sync_stack_V3_run2_2026_09_09/31","task":"Pick up the red cube and put it on top of the blue cube","label":"failure","scored":true,"source":"Alkatt/eval_LDVLA_Sync_stack_V3_run2_2026_09_09","group":"so_follower","episode":"31","predictions":{"RoboJev-27B":0.012014276092206289,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LDVLA_bfloat16_Async_sort_V3_run2_2026_10_21/6","task":"Put the red cube in the red bowl and the blue cube in the blue bowl","label":"failure","scored":true,"source":"Alkatt/eval_LDVLA_bfloat16_Async_sort_V3_run2_2026_10_21","group":"so_follower","episode":"6","predictions":{"RoboJev-27B":0.003151315981978505,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LDVLA_bfloat16_Sync_stack_V3_run6_2026_10_16/27","task":"Pick up the red cube and put it on top of the blue cube","label":"unclear","scored":false,"source":"Alkatt/eval_LDVLA_bfloat16_Sync_stack_V3_run6_2026_10_16","group":"so_follower","episode":"27","predictions":{"RoboJev-27B":0.050512417091672125,"GPT-6 Astra":0.72,"GPT-6.1 Sol":0.72,"Claude Opus 5.5":0.45,"Claude Sonnet 5.5":0.45,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LDVLA_bfloat16_Sync_pick_V3_run5_2026_10_15/42","task":"Pick up the red cube and place it in the red bowl","label":"success","scored":true,"source":"Alkatt/eval_LDVLA_bfloat16_Sync_pick_V3_run5_2026_10_15","group":"so_follower","episode":"42","predictions":{"RoboJev-27B":0.9838587664629412,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.82,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LDVLA_bfloat16_Sync_stack_V3_run3_2026_10_16/40","task":"Pick up the red cube and put it on top of the blue cube","label":"failure","scored":true,"source":"Alkatt/eval_LDVLA_bfloat16_Sync_stack_V3_run3_2026_10_16","group":"so_follower","episode":"40","predictions":{"RoboJev-27B":0.006169491991560621,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_LSVLA_float32_pick_run1_2026_08_04/29","task":"Pick up the red cube and place it in the red bowl","label":"success","scored":true,"source":"Alkatt/eval_LSVLA_float32_pick_run1_2026_08_04","group":"so_follower","episode":"29","predictions":{"RoboJev-27B":0.989146058348328,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.96,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_SMOLVLA_whiteblackcube_16_04_2026_full/6","task":"Place the white cube in the bowl.","label":"success","scored":true,"source":"Alkatt/eval_SMOLVLA_whiteblackcube_16_04_2026_full","group":"so_follower","episode":"6","predictions":{"RoboJev-27B":0.9887624065250935,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.95,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_SmolVLA_stack_V3_run2_2026_08_31/34","task":"Pick up the red cube and put it on top of the blue cube","label":"failure","scored":true,"source":"Alkatt/eval_SmolVLA_stack_V3_run2_2026_08_31","group":"so_follower","episode":"34","predictions":{"RoboJev-27B":0.006614782952327129,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_SmolVLA_pickredcube_2026_06_18/72","task":"Place the red cube in the red bowl.","label":"failure","scored":true,"source":"Alkatt/eval_SmolVLA_pickredcube_2026_06_18","group":"so_follower","episode":"72","predictions":{"RoboJev-27B":0.025085231096149192,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_SmolVLA_pickplace_run1_2026_07_21/49","task":"Pick up the red cube and place it in the red bowl","label":"success","scored":true,"source":"Alkatt/eval_SmolVLA_pickplace_run1_2026_07_21","group":"so_follower","episode":"49","predictions":{"RoboJev-27B":0.9863023857648306,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_SmolVLA_sort_V2_run1_2026_08_17/12","task":"Put the red cube in the red bowl and the blue cube in the blue bowl","label":"failure","scored":true,"source":"Alkatt/eval_SmolVLA_sort_V2_run1_2026_08_17","group":"so_follower","episode":"12","predictions":{"RoboJev-27B":0.015298596828295097,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.01,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_act_so101_CubeToBowl_ASN_FORMAL_UNSEEN_POSITIONS_20251121/73","task":"Place the cube in the bowl.","label":"failure","scored":true,"source":"Alkatt/eval_act_so101_CubeToBowl_ASN_FORMAL_UNSEEN_POSITIONS_20251121","group":"so101_follower","episode":"73","predictions":{"RoboJev-27B":0.010530690572571734,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_SmolVLA_stackredcube_2026_06_19/60","task":"Stack the red cube onto the blue cube.","label":"failure","scored":true,"source":"Alkatt/eval_SmolVLA_stackredcube_2026_06_19","group":"so_follower","episode":"60","predictions":{"RoboJev-27B":0.011297301942369706,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_SmolVLA_stack_run2_2026_08_03/3","task":"Pick up the red cube and put it on top of the blue cube","label":"success","scored":true,"source":"Alkatt/eval_SmolVLA_stack_run2_2026_08_03","group":"so_follower","episode":"3","predictions":{"RoboJev-27B":0.06162307659134308,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.82,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_SmolVLA_stack_V3_run3_2026_08_31/23","task":"Pick up the red cube and put it on top of the blue cube","label":"failure","scored":true,"source":"Alkatt/eval_SmolVLA_stack_V3_run3_2026_08_31","group":"so_follower","episode":"23","predictions":{"RoboJev-27B":0.009116839519582011,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_SmolVLA_stack_V3_run5_2026_09_01/19","task":"Pick up the red cube and put it on top of the blue cube","label":"failure","scored":true,"source":"Alkatt/eval_SmolVLA_stack_V3_run5_2026_09_01","group":"so_follower","episode":"19","predictions":{"RoboJev-27B":0.003772610060322427,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Alkatt/eval_smolvla_so101_CubeToBowl_ASN_test_20251120_002/0","task":"Place the cube in the bowl.","label":"success","scored":true,"source":"Alkatt/eval_smolvla_so101_CubeToBowl_ASN_test_20251120_002","group":"so101_follower","episode":"0","predictions":{"RoboJev-27B":0.9801539537113877,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.9,"Claude Sonnet 5.5":0.95,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"AutoRLBench/eval_push_green_button_merged/800","task":"push the green button","label":"unclear","scored":false,"source":"AutoRLBench/eval_push_green_button_merged","group":"so-101","episode":"800","predictions":{"RoboJev-27B":0.7767726790769229,"GPT-6 Astra":0.24,"GPT-6.1 Sol":0.73,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"BENVBAI/eval_so100_eraser_test/0","task":"Grasp a eraser and put it in the bowl.","label":"failure","scored":true,"source":"BENVBAI/eval_so100_eraser_test","group":"so100","episode":"0","predictions":{"RoboJev-27B":0.002901691830028414,"GPT-6 Astra":0.002,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"BetterCallSaul04/eval_evorl_smolvla_stacking_r1_redo50/37","task":"Stack the red cube on top of the white cube.","label":"success","scored":true,"source":"BetterCallSaul04/eval_evorl_smolvla_stacking_r1_redo50","group":"so_follower","episode":"37","predictions":{"RoboJev-27B":0.9916535745126864,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"BrandonAL/eval_ft60k_sorting/36","task":"Place the red cube in the right box and the blue cube in the left box.","label":"failure","scored":true,"source":"BrandonAL/eval_ft60k_sorting","group":"so101","episode":"36","predictions":{"RoboJev-27B":0.007300849386995287,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"BrandonAL/eval_smolvla_all_stacking_v3/11","task":"Put the red cube on top of the blue cube.","label":"failure","scored":true,"source":"BrandonAL/eval_smolvla_all_stacking_v3","group":"so101_follower","episode":"11","predictions":{"RoboJev-27B":0.00872173437725464,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"CZandt/eval_tape_moving_test_day_2/0","task":"Grab the tape and move it to the blue x","label":"unclear","scored":false,"source":"CZandt/eval_tape_moving_test_day_2","group":"so_follower","episode":"0","predictions":{"RoboJev-27B":0.01851136286747985,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Daiki127/eval_research_second_brown_cube/6","task":"Pick up the light brown cube and move it to the white area.","label":"failure","scored":true,"source":"Daiki127/eval_research_second_brown_cube","group":"so_follower","episode":"6","predictions":{"RoboJev-27B":0.012728580346379203,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Davidei/eval_Stack_blocks_lay7_70000/0","task":"Build a Stack, grap the red block and move it on the yellow block","label":"failure","scored":true,"source":"Davidei/eval_Stack_blocks_lay7_70000","group":"so_follower","episode":"0","predictions":{"RoboJev-27B":0.008011236983230804,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"DorayakiLin/eval_so100_pick_charger_on_tissue_060000/8","task":"Pick up the charger and put it on the white tissue.","label":"success","scored":true,"source":"DorayakiLin/eval_so100_pick_charger_on_tissue_060000","group":"so100","episode":"8","predictions":{"RoboJev-27B":0.9937869296367748,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.97,"Claude Sonnet 5.5":0.96,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"EPITECH-LILLE/eval_camera_above/51","task":"Grab the cube","label":"unclear","scored":false,"source":"EPITECH-LILLE/eval_camera_above","group":"so_follower","episode":"51","predictions":{"RoboJev-27B":0.46952689222757815,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Greedybathtub/eval_redCubePickPlace7/124","task":"Pick and place red cube","label":"failure","scored":true,"source":"Greedybathtub/eval_redCubePickPlace7","group":"so_follower","episode":"124","predictions":{"RoboJev-27B":0.035521954659196116,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"GustavoDLRA/eval_so101-11/1","task":"Grab the green lego","label":"success","scored":true,"source":"GustavoDLRA/eval_so101-11","group":"so_follower","episode":"1","predictions":{"RoboJev-27B":0.04261177077129596,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"JiabinQ/eval_pick_place_tape_16kv1/6","task":"Put the tape in the bin","label":"failure","scored":true,"source":"JiabinQ/eval_pick_place_tape_16kv1","group":"so101_follower","episode":"6","predictions":{"RoboJev-27B":0.0438311803202082,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Jiafei1224/eval_cosmos_pegboard_in-distribution/15","task":"Place Tools Onto Pegboard","label":"unclear","scored":false,"source":"Jiafei1224/eval_cosmos_pegboard_in-distribution","group":"bi_yam_follower","episode":"15","predictions":{"RoboJev-27B":0.0926097548287935,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Jiafei1224/eval_molmoact_test_tube_in-distribution/21","task":"Store Test Tubes","label":"unclear","scored":false,"source":"Jiafei1224/eval_molmoact_test_tube_in-distribution","group":"bi_yam_follower","episode":"21","predictions":{"RoboJev-27B":0.12158653372371102,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.91,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.55,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Jiafei1224/eval_openvla_test_tube_ood/5","task":"Store Test Tubes","label":"unclear","scored":false,"source":"Jiafei1224/eval_openvla_test_tube_ood","group":"bi_yam_follower","episode":"5","predictions":{"RoboJev-27B":0.22270149161293135,"GPT-6 Astra":0.78,"GPT-6.1 Sol":0.13,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Jiafei1224/eval_openvla_test_tube_in-distribution/31","task":"Store Test Tubes","label":"failure","scored":true,"source":"Jiafei1224/eval_openvla_test_tube_in-distribution","group":"bi_yam_follower","episode":"31","predictions":{"RoboJev-27B":0.24521013088980223,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.45,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Jingyi-Z/eval_act-so101-wrist-pick-place-ball-bowl-v1/53","task":"pick the red ball and place it in the plastic bowl","label":"failure","scored":true,"source":"Jingyi-Z/eval_act-so101-wrist-pick-place-ball-bowl-v1","group":"so_follower","episode":"53","predictions":{"RoboJev-27B":0.0031841103800148082,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"JoshuaYang/eval_smolvla-cloth-fold-final/0","task":"Fold the cloth into square","label":"success","scored":true,"source":"JoshuaYang/eval_smolvla-cloth-fold-final","group":"bi_so100_follower","episode":"0","predictions":{"RoboJev-27B":0.8827948010129355,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.12,"Claude Opus 5.5":0.25,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"KS325/eval_open-drawer-all-r2_expt1_lower/8","task":"Open the lower drawer.","label":"unclear","scored":false,"source":"KS325/eval_open-drawer-all-r2_expt1_lower","group":"so_follower","episode":"8","predictions":{"RoboJev-27B":0.019349791752506864,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"KS325/eval_skill-set-r1_expt1_place-upper/4","task":"Place the orange doll on the yellow plate.","label":"success","scored":true,"source":"KS325/eval_skill-set-r1_expt1_place-upper","group":"so_follower","episode":"4","predictions":{"RoboJev-27B":0.9907289766712922,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.96,"Claude Sonnet 5.5":0.95,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"KyraLeeChunWei/eval_ClariClear_E150_Trial2_Trial3_20k_100_act/9","task":"Pick up ClariClear from table","label":"unclear","scored":false,"source":"KyraLeeChunWei/eval_ClariClear_E150_Trial2_Trial3_20k_100_act","group":"franka","episode":"9","predictions":{"RoboJev-27B":0.9173585190858193,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"KyraLeeChunWei/eval_Panadol_20k_e50/12","task":"Pick up Panadol from table","label":"unclear","scored":false,"source":"KyraLeeChunWei/eval_Panadol_20k_e50","group":"franka","episode":"12","predictions":{"RoboJev-27B":0.5397252754708514,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"KyraLeeChunWei/eval_Panadol_E100_Trial2_Trial3_20k_100_act/1","task":"Pick up Panadol from table","label":"unclear","scored":false,"source":"KyraLeeChunWei/eval_Panadol_E100_Trial2_Trial3_20k_100_act","group":"franka","episode":"1","predictions":{"RoboJev-27B":0.9328542456796166,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"KyraLeeChunWei/eval_ClariClear_E100_Trial123_40k_100_act/0","task":"Pick up ClariClear from table","label":"unclear","scored":false,"source":"KyraLeeChunWei/eval_ClariClear_E100_Trial123_40k_100_act","group":"franka","episode":"0","predictions":{"RoboJev-27B":0.9051251581344624,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.82,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"KyraLeeChunWei/eval_Clariclear_20K_e50/21","task":"Pick up ClariClear from table","label":"unclear","scored":false,"source":"KyraLeeChunWei/eval_Clariclear_20K_e50","group":"franka","episode":"21","predictions":{"RoboJev-27B":0.38233666047893716,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.35,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"KyraLeeChunWei/eval_Real_Panda_Polymetis_Acetylcysteine_E50_20K_100_act_ep10/4","task":"Pick up Acetylcysteine from table","label":"unclear","scored":false,"source":"KyraLeeChunWei/eval_Real_Panda_Polymetis_Acetylcysteine_E50_20K_100_act_ep10","group":"franka","episode":"4","predictions":{"RoboJev-27B":0.10745821263239567,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Mohamedal/eval_act_so100_plum_multi_/5","task":"put the plum in the red bowl.","label":"failure","scored":true,"source":"Mohamedal/eval_act_so100_plum_multi_","group":"so100","episode":"5","predictions":{"RoboJev-27B":0.003259193317952129,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"MrPsarik/eval_t/49","task":"Move yellow block","label":"unclear","scored":false,"source":"MrPsarik/eval_t","group":"so101_follower","episode":"49","predictions":{"RoboJev-27B":0.9331872736394863,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Odog16/eval_act_lekiwi_test_0.11/6","task":"Pick up the sock and place it in the basket.","label":"unclear","scored":false,"source":"Odog16/eval_act_lekiwi_test_0.11","group":"lekiwi","episode":"6","predictions":{"RoboJev-27B":0.034439008440594,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Ofiroz91/eval_so_100_cube2bowl/4","task":"placing cube inside a red bawl","label":"success","scored":true,"source":"Ofiroz91/eval_so_100_cube2bowl","group":"so100","episode":"4","predictions":{"RoboJev-27B":0.9704127592613233,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Philmat/eval_100kstep_picko-v7-180eps_act4/3","task":"Pick up blue cube and place it into the round yellow ring","label":"unclear","scored":false,"source":"Philmat/eval_100kstep_picko-v7-180eps_act4","group":"so100_follower","episode":"3","predictions":{"RoboJev-27B":0.024362607529127646,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Qiu-Xinchuan/eval_so101_bimanual_total_0/68","task":"Stack the right bowl onto the left bowl.","label":"failure","scored":true,"source":"Qiu-Xinchuan/eval_so101_bimanual_total_0","group":"bi_so_follower","episode":"68","predictions":{"RoboJev-27B":0.04789060895249678,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"RickRain/eval_1_0_IP2/3","task":"\\!Imperio Grap the block and place it onto the black square","label":"failure","scored":true,"source":"RickRain/eval_1_0_IP2","group":"so_follower","episode":"3","predictions":{"RoboJev-27B":0.0046221648012202705,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"S-sirigiri/eval_mug_drag_test/4","task":"{'Repeat until no yellow objects remain': 'pick up one yellow object, place it in the saucer, release it, then move on to the next yellow object.'}","label":"unclear","scored":false,"source":"S-sirigiri/eval_mug_drag_test","group":"so_follower","episode":"4","predictions":{"RoboJev-27B":0.015396820987081367,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Sebastian-07/eval_sort-01-03/1","task":"Sort the pieces by colour","label":"failure","scored":true,"source":"Sebastian-07/eval_sort-01-03","group":"so_follower","episode":"1","predictions":{"RoboJev-27B":0.02435202666978518,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"SryTaisei/eval_blockcube100_model2/8","task":"Grab the black cube","label":"unclear","scored":false,"source":"SryTaisei/eval_blockcube100_model2","group":"so_follower","episode":"8","predictions":{"RoboJev-27B":0.5817997075444787,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"TheMuz/eval_kirby_v2_main/0","task":"Pick up Kirby and place him in the bowl","label":"success","scored":true,"source":"TheMuz/eval_kirby_v2_main","group":"so_follower","episode":"0","predictions":{"RoboJev-27B":0.9927630166161526,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.96,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Yunrufeng000/eval_pi05_so101/16","task":"Stack the block on the right on top of the block on the left","label":"failure","scored":true,"source":"Yunrufeng000/eval_pi05_so101","group":"so101_follower","episode":"16","predictions":{"RoboJev-27B":0.00023273632721515896,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"Zekai-Chen/eval_bi_so101_round1_4cam/318","task":"Fold the towel","label":"success","scored":true,"source":"Zekai-Chen/eval_bi_so101_round1_4cam","group":"bi_so_follower","episode":"318","predictions":{"RoboJev-27B":0.9310852676009953,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"aakashv100/eval_so101-pick-cube-v2-smolvla-fixed/33","task":"Pick up the cube and place it in the bowl","label":"success","scored":true,"source":"aakashv100/eval_so101-pick-cube-v2-smolvla-fixed","group":"so_follower","episode":"33","predictions":{"RoboJev-27B":0.9561345005724619,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"aboyarov/eval_redblock-2-cameras-test/1","task":"Test of depth camera","label":"unclear","scored":false,"source":"aboyarov/eval_redblock-2-cameras-test","group":"so_follower","episode":"1","predictions":{"RoboJev-27B":0.6988897242864717,"GPT-6 Astra":0.75,"GPT-6.1 Sol":0.8,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"allenai/eval_molmoact_pipette_in-distribution/6","task":"Attach Tip To Pipette","label":"success","scored":true,"source":"allenai/eval_molmoact_pipette_in-distribution","group":"bi_yam_follower","episode":"6","predictions":{"RoboJev-27B":0.9581024293621048,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"allenai/eval_molmoact_pipette_ood/3","task":"Attach Tip To Pipette","label":"unclear","scored":false,"source":"allenai/eval_molmoact_pipette_ood","group":"bi_yam_follower","episode":"3","predictions":{"RoboJev-27B":0.9666939805153348,"GPT-6 Astra":0.9,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"allenai/eval_cosmos_pipette_in-distribution/43","task":"Attach Tip To Pipette","label":"unclear","scored":false,"source":"allenai/eval_cosmos_pipette_in-distribution","group":"bi_yam_follower","episode":"43","predictions":{"RoboJev-27B":0.9417466981963536,"GPT-6 Astra":0.93,"GPT-6.1 Sol":0.9,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"allenai/eval_xvla_linearbot_in-distribution/0","task":"Place Popcorn Into Microwave","label":"unclear","scored":false,"source":"allenai/eval_xvla_linearbot_in-distribution","group":"bi_yam_linear_bot","episode":"0","predictions":{"RoboJev-27B":0.10481839020485369,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"allenai/eval_pi05_test_tube_ood/8","task":"Store Test Tubes","label":"unclear","scored":false,"source":"allenai/eval_pi05_test_tube_ood","group":"bi_yam_follower","episode":"8","predictions":{"RoboJev-27B":0.03812062413727405,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"allenai/eval_pi05_test_tube_in-distribution/28","task":"Store Test Tubes","label":"unclear","scored":false,"source":"allenai/eval_pi05_test_tube_in-distribution","group":"bi_yam_follower","episode":"28","predictions":{"RoboJev-27B":0.2353934729812947,"GPT-6 Astra":0.87,"GPT-6.1 Sol":0.86,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"allenai/eval_xvla_pegboard_in-distribution/50","task":"Place Tools Onto Pegboard","label":"failure","scored":true,"source":"allenai/eval_xvla_pegboard_in-distribution","group":"bi_yam_follower","episode":"50","predictions":{"RoboJev-27B":0.033683181076118875,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"aravindhs-NV/eval_pickpens50_0220_ah8/5","task":"Pick up the screwdriver and put it in the tray","label":"unclear","scored":false,"source":"aravindhs-NV/eval_pickpens50_0220_ah8","group":"so101_follower","episode":"5","predictions":{"RoboJev-27B":0.00866289043926733,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"armnet/eval_assemble_rail_pi05_fft_step20000_ep1to35/19","task":"Assemble the rail from its parts","label":"unclear","scored":false,"source":"armnet/eval_assemble_rail_pi05_fft_step20000_ep1to35","group":"lerobot/bimanual_yam","episode":"19","predictions":{"RoboJev-27B":0.07515015698474424,"GPT-6 Astra":0.72,"GPT-6.1 Sol":0.78,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"armnet/eval_push_green_button_06h59m_29-sep-2026/15","task":"Push the green button.","label":"unclear","scored":false,"source":"armnet/eval_push_green_button_06h59m_29-sep-2026","group":"so-101","episode":"15","predictions":{"RoboJev-27B":0.7493005579219434,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.15,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"asafxrev/eval_act_so100_jenga_box_simple_2_2/1","task":"Grasp a Jenga piece and put it on top of the box","label":"success","scored":true,"source":"asafxrev/eval_act_so100_jenga_box_simple_2_2","group":"so100","episode":"1","predictions":{"RoboJev-27B":0.8273563300473746,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"arrg-unam/eval_act_omx_Test1004_00/44","task":"Pick the red cubic_2","label":"success","scored":true,"source":"arrg-unam/eval_act_omx_Test1004_00","group":"omx_follower","episode":"44","predictions":{"RoboJev-27B":0.8463475252963695,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"asdl-unist/eval_test1-128LR-128A-5epch/8","task":"Pick up a carrot and place it in the blue bowl.","label":"success","scored":true,"source":"asdl-unist/eval_test1-128LR-128A-5epch","group":"so_follower","episode":"8","predictions":{"RoboJev-27B":0.9937697552676431,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"asdl-unist/eval_pickcarrot-pi0-libero-12k-1/3","task":"Pick up a carrot and place it in the blue bowl.","label":"failure","scored":true,"source":"asdl-unist/eval_pickcarrot-pi0-libero-12k-1","group":"so_follower","episode":"3","predictions":{"RoboJev-27B":0.0029206226925583196,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.01,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"av120/eval_record-test-2-cameras94-new/3","task":"Pick up the gray cube and place it in the yellow bin","label":"failure","scored":true,"source":"av120/eval_record-test-2-cameras94-new","group":"so_follower","episode":"3","predictions":{"RoboJev-27B":0.0008778494461697696,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"bluephysi01/eval_act_so101_test26-1-3/4","task":"Pick up the doll and place it into the basket","label":"failure","scored":true,"source":"bluephysi01/eval_act_so101_test26-1-3","group":"so101_follower","episode":"4","predictions":{"RoboJev-27B":0.007163614329122071,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"bluephysi01/eval_xvla-100000-cs30-as30-1/0","task":"Transfer bottle from random position to cup via handover","label":"failure","scored":true,"source":"bluephysi01/eval_xvla-100000-cs30-as30-1","group":"bi_so_follower","episode":"0","predictions":{"RoboJev-27B":0.04505028645479108,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"camilasfeijoo/eval_swlejepsters/2","task":"Sweep Red Block","label":"success","scored":true,"source":"camilasfeijoo/eval_swlejepsters","group":"so101_follower","episode":"2","predictions":{"RoboJev-27B":0.95716901907329,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"chy626/eval_bread_plate_merged1/8","task":"Pick the bread and place it in the plate","label":"success","scored":true,"source":"chy626/eval_bread_plate_merged1","group":"so_follower","episode":"8","predictions":{"RoboJev-27B":0.993939400694463,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.999,"Claude Opus 5.5":0.97,"Claude Sonnet 5.5":0.96,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"continuallearning/eval_dit_posttrainv2_clare_dit_0_2_real_2_on_real_1_seed1000/4","task":"stack the orange bowl on the other bowls","label":"success","scored":true,"source":"continuallearning/eval_dit_posttrainv2_clare_dit_0_2_real_2_on_real_1_seed1000","group":"franka","episode":"4","predictions":{"RoboJev-27B":0.9771167957683531,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"continuallearning/eval_dit_posttrainv2_clare_dit_real_1_on_real_0_seed1000/6","task":"put the bowl on the plate","label":"success","scored":true,"source":"continuallearning/eval_dit_posttrainv2_clare_dit_real_1_on_real_0_seed1000","group":"franka","episode":"6","predictions":{"RoboJev-27B":0.7885183275127721,"GPT-6 Astra":0.35,"GPT-6.1 Sol":0.76,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"continuallearning/eval_dit_posttrainv2_clare_dit_cond_proj_real_1_on_real_1_seed1000/3","task":"stack the orange bowl on the other bowls","label":"failure","scored":true,"source":"continuallearning/eval_dit_posttrainv2_clare_dit_cond_proj_real_1_on_real_1_seed1000","group":"franka","episode":"3","predictions":{"RoboJev-27B":0.0049695992736324725,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"continuallearning/eval_dit_posttrainv2_clare_dit_real_3_on_real_1_seed1000/1","task":"stack the orange bowl on the other bowls","label":"failure","scored":true,"source":"continuallearning/eval_dit_posttrainv2_clare_dit_real_3_on_real_1_seed1000","group":"franka","episode":"1","predictions":{"RoboJev-27B":0.23312313208007088,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"continuallearning/eval_dit_posttrainv2_clare_dit_real_3_on_real_0_seed1000/6","task":"put the bowl on the plate","label":"success","scored":true,"source":"continuallearning/eval_dit_posttrainv2_clare_dit_real_3_on_real_0_seed1000","group":"franka","episode":"6","predictions":{"RoboJev-27B":0.9850732277524099,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"continuallearning/eval_dit_posttrainv2_union_norm_seqlora_real_0_on_real_0_seed1000/8","task":"put the bowl on the plate","label":"success","scored":true,"source":"continuallearning/eval_dit_posttrainv2_union_norm_seqlora_real_0_on_real_0_seed1000","group":"franka","episode":"8","predictions":{"RoboJev-27B":0.9871775515505502,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"davidgoss/eval_act_so100_test1/1","task":"Put cubes into drawers.","label":"unclear","scored":false,"source":"davidgoss/eval_act_so100_test1","group":"so100","episode":"1","predictions":{"RoboJev-27B":0.21877358900968744,"GPT-6 Astra":0.82,"GPT-6.1 Sol":0.82,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"davidgoss/eval_smolvla_test3/5","task":"Grab the cube","label":"unclear","scored":false,"source":"davidgoss/eval_smolvla_test3","group":"so100_follower","episode":"5","predictions":{"RoboJev-27B":0.354916012599645,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"dc2ac/eval_act_so100_t2/9","task":"Grasp a bunny and put it in the bin.","label":"failure","scored":true,"source":"dc2ac/eval_act_so100_t2","group":"so100","episode":"9","predictions":{"RoboJev-27B":0.036098882493170316,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"dopaul/eval_100_rooks_act_100k_16jul/3","task":"Move the chess piece from red to blue","label":"failure","scored":true,"source":"dopaul/eval_100_rooks_act_100k_16jul","group":"so100_follower","episode":"3","predictions":{"RoboJev-27B":0.025138421961949542,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"dureduck/eval_so100_act_1109_lp_2loc_5x4_20samples_b8_20trials/6","task":"lift up and put down the gray container","label":"success","scored":true,"source":"dureduck/eval_so100_act_1109_lp_2loc_5x4_20samples_b8_20trials","group":"so100_follower","episode":"6","predictions":{"RoboJev-27B":0.9032475053453003,"GPT-6 Astra":0.91,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"edwardyeung04/eval_cat_bowl_5obs/1","task":"Put cat in bowl","label":"unclear","scored":false,"source":"edwardyeung04/eval_cat_bowl_5obs","group":"so_follower","episode":"1","predictions":{"RoboJev-27B":0.02562970997143366,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"ethanCSL/eval_steering_paper_high_10/4","task":"Put the red cube in the box.","label":"unclear","scored":false,"source":"ethanCSL/eval_steering_paper_high_10","group":"koch_follower","episode":"4","predictions":{"RoboJev-27B":0.9575946756031377,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.7,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"ethanCSL/eval_steering_paper_baseline/12","task":"Put the red cube in the box.","label":"success","scored":true,"source":"ethanCSL/eval_steering_paper_baseline","group":"koch_follower","episode":"12","predictions":{"RoboJev-27B":0.9673947813203297,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.95,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.65,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"fabiangrob/eval_act_c100_b20_shakiness_20260301_233129/8","task":"Pick orange cube and place it in the blue container","label":"failure","scored":true,"source":"fabiangrob/eval_act_c100_b20_shakiness_20260301_233129","group":"so101_follower","episode":"8","predictions":{"RoboJev-27B":0.01597712144419907,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"fabiangrob/eval_act_c100_b10_shakiness_20260301_153356/17","task":"Pick orange cube and place it in the blue container","label":"failure","scored":true,"source":"fabiangrob/eval_act_c100_b10_shakiness_20260301_153356","group":"so101_follower","episode":"17","predictions":{"RoboJev-27B":0.00817383040505974,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"fbsh96/eval_so101_sock_ball_dualcam_act_202605030846/0","task":"Pick up one sock ball from a marked black dot and place it into the yellow square target area.","label":"failure","scored":true,"source":"fbsh96/eval_so101_sock_ball_dualcam_act_202605030846","group":"bi_so101_follower","episode":"0","predictions":{"RoboJev-27B":0.009530439684468555,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"guanfengliu/eval_evo1_50k/2","task":"place green block into bin","label":"success","scored":true,"source":"guanfengliu/eval_evo1_50k","group":"so101_follower","episode":"2","predictions":{"RoboJev-27B":0.9339315241095862,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"guanfengliu/eval_so101_main_bin_2cameras_new_80k_red2/4","task":"Put block into bin","label":"failure","scored":true,"source":"guanfengliu/eval_so101_main_bin_2cameras_new_80k_red2","group":"so101_follower","episode":"4","predictions":{"RoboJev-27B":0.015236841341218605,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"guanfengliu/eval_so101_main_bin_2cameras_web2_180k/2","task":"Put block into bin","label":"success","scored":true,"source":"guanfengliu/eval_so101_main_bin_2cameras_web2_180k","group":"so101_follower","episode":"2","predictions":{"RoboJev-27B":0.9741014391795698,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.96,"Claude Sonnet 5.5":0.95,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"hbseong/eval_record-pick-and-place-so101_baseline/6","task":"Pick the blue cube, and place it in the pink box.","label":"success","scored":true,"source":"hbseong/eval_record-pick-and-place-so101_baseline","group":"so101_follower","episode":"6","predictions":{"RoboJev-27B":0.9895713487694665,"GPT-6 Astra":0.995,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.97,"Claude Sonnet 5.5":0.96,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"hbseong/eval_record-pick-and-place-so101_ft-3ep/6","task":"Pick the blue cube, and place it in the pink box.","label":"failure","scored":true,"source":"hbseong/eval_record-pick-and-place-so101_ft-3ep","group":"so101_follower","episode":"6","predictions":{"RoboJev-27B":0.007419692947664747,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"hcisbmm/eval_yam-loosen-bottle_act/1","task":"Loosen the bottle cap and hand over","label":"unclear","scored":false,"source":"hcisbmm/eval_yam-loosen-bottle_act","group":"bi_yam_follower","episode":"1","predictions":{"RoboJev-27B":0.07375099817919833,"GPT-6 Astra":0.06,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"iptihar/eval_act_so101_grasp_100_v3_20/5","task":"Grab the cube","label":"unclear","scored":false,"source":"iptihar/eval_act_so101_grasp_100_v3_20","group":"so_follower","episode":"5","predictions":{"RoboJev-27B":0.4869558348951159,"GPT-6 Astra":0.05,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.12,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"jian001/eval_smolvla_so101_GGorBB1-3/0","task":"Only grab the green bar.","label":"unclear","scored":false,"source":"jian001/eval_smolvla_so101_GGorBB1-3","group":"so101_follower","episode":"0","predictions":{"RoboJev-27B":0.03603714924223794,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.07,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"johannesschirrmeister/eval_3poses_groot/4","task":"Place green rectangle into the tape.","label":"success","scored":true,"source":"johannesschirrmeister/eval_3poses_groot","group":"so100_follower","episode":"4","predictions":{"RoboJev-27B":0.989267298975735,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.96,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"kiroaiseoul/eval_act_task08_14D_90data_200k/11","task":"Take out the stored beaker and put the held beaker into the fridge","label":"failure","scored":true,"source":"kiroaiseoul/eval_act_task08_14D_90data_200k","group":"mobileai_robot","episode":"11","predictions":{"RoboJev-27B":0.08042327456188342,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"kiroaiseoul/eval_act_task08_task09_mixed_14D_440data_200k/19","task":"Take out the stored beaker and put the held beaker into the fridge and Close the fridge door while holding the beaker","label":"unclear","scored":false,"source":"kiroaiseoul/eval_act_task08_task09_mixed_14D_440data_200k","group":"mobileai_robot","episode":"19","predictions":{"RoboJev-27B":0.8307696588022173,"GPT-6 Astra":0.05,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.62,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"kiroaiseoul/eval_najy_1014_1624_hot_t02_e60/0","task":"Pick up the two tubes from the rack with both hands","label":"unclear","scored":false,"source":"kiroaiseoul/eval_najy_1014_1624_hot_t02_e60","group":"mobileai_robot","episode":"0","predictions":{"RoboJev-27B":0.01656992430642358,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"kiroaiseoul/eval_task10_act_base_0924_2251/8","task":"Move to the beaker storage shelf","label":"unclear","scored":false,"source":"kiroaiseoul/eval_task10_act_base_0924_2251","group":"mobileai_robot","episode":"8","predictions":{"RoboJev-27B":0.9111012969352502,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"kissyour/eval_my_smolvla_test01/0","task":"Grab the toy","label":"unclear","scored":false,"source":"kissyour/eval_my_smolvla_test01","group":"so_follower","episode":"0","predictions":{"RoboJev-27B":0.06069001883322614,"GPT-6 Astra":0.79,"GPT-6.1 Sol":0.84,"Claude Opus 5.5":0.25,"Claude Sonnet 5.5":0.35,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"kivod/eval_act_pruned30/5","task":"Grasp a cucumber and put it in the hole.","label":"failure","scored":true,"source":"kivod/eval_act_pruned30","group":"so100","episode":"5","predictions":{"RoboJev-27B":0.016614315152284155,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"kivod/eval_act_pruned40/11","task":"Grasp a cucumber and put it in the hole.","label":"failure","scored":true,"source":"kivod/eval_act_pruned40","group":"so100","episode":"11","predictions":{"RoboJev-27B":0.01681552301383725,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"komokomo7/eval_act20260113_100607/0","task":"Pick up the object","label":"unclear","scored":false,"source":"komokomo7/eval_act20260113_100607","group":"cranex7_follower","episode":"0","predictions":{"RoboJev-27B":0.170300343162709,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"komokomo7/eval_act20260126_214337/11","task":"Pick up the object","label":"unclear","scored":false,"source":"komokomo7/eval_act20260126_214337","group":"cranex7_follower","episode":"11","predictions":{"RoboJev-27B":0.8227887129536363,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"komokomo7/eval_act20260126_220016/16","task":"Pick up the object","label":"unclear","scored":false,"source":"komokomo7/eval_act20260126_220016","group":"cranex7_follower","episode":"16","predictions":{"RoboJev-27B":0.9079009666551356,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"komokomo7/eval_act_no_sensor_20260126_222826/13","task":"Pick up the object","label":"unclear","scored":false,"source":"komokomo7/eval_act_no_sensor_20260126_222826","group":"cranex7_follower","episode":"13","predictions":{"RoboJev-27B":0.876956152917432,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.03,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"komokomo7/eval_act_joint_top_sensor_20260523_133030/17","task":"Pick up the object","label":"unclear","scored":false,"source":"komokomo7/eval_act_joint_top_sensor_20260523_133030","group":"cranex7_follower","episode":"17","predictions":{"RoboJev-27B":0.7641306410985307,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"komokomo7/eval_act_no_sensor_20260610_172448/7","task":"Pick up the object","label":"unclear","scored":false,"source":"komokomo7/eval_act_no_sensor_20260610_172448","group":"cranex7_follower","episode":"7","predictions":{"RoboJev-27B":0.9439029021611985,"GPT-6 Astra":0.08,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"kumarhans/eval_tranciever-test-merged-simple/4","task":"Plug in Tranciever","label":"failure","scored":true,"source":"kumarhans/eval_tranciever-test-merged-simple","group":"openarm_follower","episode":"4","predictions":{"RoboJev-27B":0.6733337470056354,"GPT-6 Astra":0.84,"GPT-6.1 Sol":0.8,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"lhund/eval_stois-paper-pickplace-V4/14","task":"Grab the lego brick and place it in the box","label":"success","scored":true,"source":"lhund/eval_stois-paper-pickplace-V4","group":"so101_follower","episode":"14","predictions":{"RoboJev-27B":0.9888331691133114,"GPT-6 Astra":0.995,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.97,"Claude Sonnet 5.5":0.96,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"liuhuanjim013/eval_act_so100_block/30","task":"Grasp a lego block and put it in the bin.","label":"unclear","scored":false,"source":"liuhuanjim013/eval_act_so100_block","group":"so100","episode":"30","predictions":{"RoboJev-27B":0.013388580468275055,"GPT-6 Astra":0.06,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"liuhuanjim013/eval_act_so100_block.bak/32","task":"Grasp a lego block and put it in the bin.","label":"failure","scored":true,"source":"liuhuanjim013/eval_act_so100_block.bak","group":"so100","episode":"32","predictions":{"RoboJev-27B":0.0054300217302086584,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"lkulowski/eval_bandu_vase_02/7","task":"Stack the vase-shaped block on the bandu platform","label":"success","scored":true,"source":"lkulowski/eval_bandu_vase_02","group":"so101_follower","episode":"7","predictions":{"RoboJev-27B":0.993026310569881,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"lucazanett/eval_act_wiping_video_adaptive/4","task":"Wipe the white board clean.","label":"success","scored":true,"source":"lucazanett/eval_act_wiping_video_adaptive","group":"custom_manipulator","episode":"4","predictions":{"RoboJev-27B":0.9737427198262655,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.96,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"masato-ka/eval_random-sim-pick-and-place-v2/17","task":"Pick up a blue cube and place on white plate.","label":"success","scored":true,"source":"masato-ka/eval_random-sim-pick-and-place-v2","group":"gym_soarm","episode":"17","predictions":{"RoboJev-27B":0.13852808875393566,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.55,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"matthewwoodc0/eval_testing_gui_run_4/23","task":"Pick up the white block and place it in the bin","label":"failure","scored":true,"source":"matthewwoodc0/eval_testing_gui_run_4","group":"so_follower","episode":"23","predictions":{"RoboJev-27B":0.0024741539206735693,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"miketangmk/eval_so101-5/37","task":"Put Red brick in round box, Blue brick in Square box","label":"unclear","scored":false,"source":"miketangmk/eval_so101-5","group":"so101_follower","episode":"37","predictions":{"RoboJev-27B":0.035328895150723676,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"miladgholami/eval_fixedrig_rectified_condC/6","task":"Pick up the scissors and put it in the yellow basket","label":"failure","scored":true,"source":"miladgholami/eval_fixedrig_rectified_condC","group":"so_follower","episode":"6","predictions":{"RoboJev-27B":0.08365884277199505,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.05,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.05,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"miladgholami/eval_liverectify_rectified_samepos/7","task":"Pick up the scissors and put it in the yellow basket","label":"failure","scored":true,"source":"miladgholami/eval_liverectify_rectified_samepos","group":"so_follower","episode":"7","predictions":{"RoboJev-27B":0.01723256773884978,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"miladgholami/eval_posevary_baseline_condA/5","task":"Pick up the scissors and put it in the yellow basket","label":"success","scored":true,"source":"miladgholami/eval_posevary_baseline_condA","group":"so_follower","episode":"5","predictions":{"RoboJev-27B":0.9912754545405318,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.97,"Claude Sonnet 5.5":0.96,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"miladgholami/eval_vit_rectified_seenpos_15deg/7","task":"Pick up the scissor and put it in the yellow basket","label":"success","scored":true,"source":"miladgholami/eval_vit_rectified_seenpos_15deg","group":"so_follower","episode":"7","predictions":{"RoboJev-27B":0.9589316108893192,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"miladgholami/eval_vit_rectified_seenpos_0deg/5","task":"Pick up the scissor and put it in the yellow basket","label":"failure","scored":true,"source":"miladgholami/eval_vit_rectified_seenpos_0deg","group":"so_follower","episode":"5","predictions":{"RoboJev-27B":0.02096054567613466,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.04,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"mimozah/eval_make_sandwhich/29","task":"Make sandwich on plate","label":"failure","scored":true,"source":"mimozah/eval_make_sandwhich","group":"so101_follower","episode":"29","predictions":{"RoboJev-27B":0.07189453509706817,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"nduque/eval_robustness_e6/67","task":"Grasp a green dice and put it in the bin.","label":"unclear","scored":false,"source":"nduque/eval_robustness_e6","group":"koch","episode":"67","predictions":{"RoboJev-27B":0.007031547228883549,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"nduque/eval_robustness_e9_3_full_dp_local_260k/173","task":"Grasp a green dice and put it in the bin.","label":"success","scored":true,"source":"nduque/eval_robustness_e9_3_full_dp_local_260k","group":"koch","episode":"173","predictions":{"RoboJev-27B":0.9848534344452007,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.96,"Claude Opus 5.5":0.85,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"nduque/eval_robustness_e9_3_full_dp_local_300k/17","task":"Grasp a green dice and put it in the bin.","label":"unclear","scored":false,"source":"nduque/eval_robustness_e9_3_full_dp_local_300k","group":"koch","episode":"17","predictions":{"RoboJev-27B":0.9763166635581348,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.66,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"nduque/eval_robustness_e9_3_full_dp_cluster_cptest/5","task":"Grasp a green dice and put it in the bin.","label":"unclear","scored":false,"source":"nduque/eval_robustness_e9_3_full_dp_cluster_cptest","group":"koch","episode":"5","predictions":{"RoboJev-27B":0.8606404459601642,"GPT-6 Astra":0.85,"GPT-6.1 Sol":0.85,"Claude Opus 5.5":0.66,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"nduque/eval_robustness_e9_3_full_og_cluster_180k/161","task":"Grasp a green dice and put it in the bin.","label":"unclear","scored":false,"source":"nduque/eval_robustness_e9_3_full_og_cluster_180k","group":"koch","episode":"161","predictions":{"RoboJev-27B":0.9517919782527129,"GPT-6 Astra":0.94,"GPT-6.1 Sol":0.91,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"nduque/eval_robustness_e9_3_full_fk_local_240k/41","task":"Grasp a green dice and put it in the bin.","label":"unclear","scored":false,"source":"nduque/eval_robustness_e9_3_full_fk_local_240k","group":"koch","episode":"41","predictions":{"RoboJev-27B":0.9308310109672122,"GPT-6 Astra":0.06,"GPT-6.1 Sol":0.08,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.4,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"northhycao/eval_act_so101_fixed/3","task":"Grasp the red cubes and put them on the white towel","label":"success","scored":true,"source":"northhycao/eval_act_so101_fixed","group":"so101_follower","episode":"3","predictions":{"RoboJev-27B":0.6732148102915699,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"oordonez/eval_campus_connect_demo_smolVLA/24","task":"Grasp the blue bone and place it inside of the box.","label":"failure","scored":true,"source":"oordonez/eval_campus_connect_demo_smolVLA","group":"multi_robot_2","episode":"24","predictions":{"RoboJev-27B":0.013461633091793027,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"pginfinity/eval_policy_testing30_1/0","task":"pick and place pcb","label":"success","scored":true,"source":"pginfinity/eval_policy_testing30_1","group":"so_follower","episode":"0","predictions":{"RoboJev-27B":0.992112341891471,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.97,"Claude Sonnet 5.5":0.96,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"pravsels/eval_push_green_button_12h29m_05-oct-2026/3","task":"Push the green button.","label":"unclear","scored":false,"source":"pravsels/eval_push_green_button_12h29m_05-oct-2026","group":"so-101","episode":"3","predictions":{"RoboJev-27B":0.6538220083080514,"GPT-6 Astra":0.89,"GPT-6.1 Sol":0.83,"Claude Opus 5.5":0.25,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"pravsels/eval_push_green_button_16h19m_05-oct-2026/1954","task":"Push the green button.","label":"unclear","scored":false,"source":"pravsels/eval_push_green_button_16h19m_05-oct-2026","group":"so-101","episode":"1954","predictions":{"RoboJev-27B":0.4007981105734028,"GPT-6 Astra":0.12,"GPT-6.1 Sol":0.12,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"puneetpanwar/eval_so101_act_table_cleanup3/0","task":"Put the pens into pen holder","label":"failure","scored":true,"source":"puneetpanwar/eval_so101_act_table_cleanup3","group":"so101_follower","episode":"0","predictions":{"RoboJev-27B":0.014959312008954489,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"refigo/eval_act_real_sweep_250828/7","task":"Sweep a block from the black area to the white area","label":"success","scored":true,"source":"refigo/eval_act_real_sweep_250828","group":"so101_follower","episode":"7","predictions":{"RoboJev-27B":0.9882479535866402,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"ricky0526/eval_so101_move_block/54","task":"Put the green block into the plate on the left.","label":"success","scored":true,"source":"ricky0526/eval_so101_move_block","group":"so101_follower","episode":"54","predictions":{"RoboJev-27B":0.9936435255152924,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.88,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"sergiov2000/eval_act_so100_leader_push_d/2","task":"Push the ball into the area enclosed by the lego structure.","label":"success","scored":true,"source":"sergiov2000/eval_act_so100_leader_push_d","group":"so100","episode":"2","predictions":{"RoboJev-27B":0.9907355768662091,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"seriintan/eval_act_picking_scissor_AprilTag_v2_100k/8","task":"Grab the scissor and put in the yellow basket","label":"failure","scored":true,"source":"seriintan/eval_act_picking_scissor_AprilTag_v2_100k","group":"so_follower","episode":"8","predictions":{"RoboJev-27B":0.1637914790913028,"GPT-6 Astra":0.02,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"seriintan/eval_baseline_v7/9","task":"Pick up the scissor and put it in the yellow basket","label":"success","scored":true,"source":"seriintan/eval_baseline_v7","group":"so_follower","episode":"9","predictions":{"RoboJev-27B":0.9692173979364659,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.9,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"seriintan/eval_frazier_v2/6","task":"Pick up the Frazier Suction Tube and place it in the blue basket","label":"success","scored":true,"source":"seriintan/eval_frazier_v2","group":"so_follower","episode":"6","predictions":{"RoboJev-27B":0.9943669895207101,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.97,"Claude Sonnet 5.5":0.96,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"seriintan/eval_spatialPE_v6_crossattn/17","task":"Pick up the scissor and put it in the yellow basket","label":"failure","scored":true,"source":"seriintan/eval_spatialPE_v6_crossattn","group":"so_follower","episode":"17","predictions":{"RoboJev-27B":0.8912690161335828,"GPT-6 Astra":0.91,"GPT-6.1 Sol":0.9,"Claude Opus 5.5":0.68,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"seriintan/eval_retractor1/19","task":"Pick up the Mastoid Retractor and place it in the blue basket","label":"success","scored":true,"source":"seriintan/eval_retractor1","group":"so_follower","episode":"19","predictions":{"RoboJev-27B":0.970945476772486,"GPT-6 Astra":0.98,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"seriintan/eval_spatialPE_v7_noCA_round1/2","task":"Pick up the scissor and put it in the yellow basket","label":"failure","scored":true,"source":"seriintan/eval_spatialPE_v7_noCA_round1","group":"so_follower","episode":"2","predictions":{"RoboJev-27B":0.9148667719230142,"GPT-6 Astra":0.9,"GPT-6.1 Sol":0.88,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.85,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"sha-abhishek/eval_record-test-3cams/3","task":"Grab the red cube","label":"success","scored":true,"source":"sha-abhishek/eval_record-test-3cams","group":"so101_follower","episode":"3","predictions":{"RoboJev-27B":0.9754581169034575,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.72,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"shunsmae/eval_so101_pickplace_pi0/0","task":"Pick up the blue block and place it in the black container","label":"unclear","scored":false,"source":"shunsmae/eval_so101_pickplace_pi0","group":"so101_follower","episode":"0","predictions":{"RoboJev-27B":0.019985811392631947,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"shylee/eval_6_Stochastic_BID/6","task":"Grasp a pengrip and put it in the cup.","label":"failure","scored":true,"source":"shylee/eval_6_Stochastic_BID","group":"so100","episode":"6","predictions":{"RoboJev-27B":0.006702682022387705,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"skywangxy/eval_baselinetest/9","task":"block pick and place","label":"unclear","scored":false,"source":"skywangxy/eval_baselinetest","group":"so_follower","episode":"9","predictions":{"RoboJev-27B":0.9827655930196681,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.8,"Claude Sonnet 5.5":0.8,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"skywangxy/eval_phasegatetest0607_35k_0.02/2","task":"block pick and place","label":"unclear","scored":false,"source":"skywangxy/eval_phasegatetest0607_35k_0.02","group":"so_follower","episode":"2","predictions":{"RoboJev-27B":0.8864316669417955,"GPT-6 Astra":0.86,"GPT-6.1 Sol":0.85,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.6,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"stevenoh2003/eval_act_so100_usb/0","task":"Grasp a lego block and put it in the bin.","label":"failure","scored":true,"source":"stevenoh2003/eval_act_so100_usb","group":"so100","episode":"0","predictions":{"RoboJev-27B":0.4145037741494884,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"sun-robot/eval_amazinghand_color_sort_v2_evo_hil/23","task":"Put the blue block into the black box.","label":"success","scored":true,"source":"sun-robot/eval_amazinghand_color_sort_v2_evo_hil","group":"amazinghand","episode":"23","predictions":{"RoboJev-27B":0.9914591619871591,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.97,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"swpark5/eval_acm_pickandplace_v3/19","task":"Grab the wooden cube and place it to a black box","label":"failure","scored":true,"source":"swpark5/eval_acm_pickandplace_v3","group":"so101_follower","episode":"19","predictions":{"RoboJev-27B":0.004797545487330677,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"swarajgosavi/eval_act_kikobot_block_real/8","task":"pick and place","label":"unclear","scored":false,"source":"swarajgosavi/eval_act_kikobot_block_real","group":"so100","episode":"8","predictions":{"RoboJev-27B":0.008678272166603905,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"swpark5/eval_acm_with_temporal_ensemble_pickandplace_v3/0","task":"Grab the wooden cube and place it to a black box","label":"failure","scored":true,"source":"swpark5/eval_acm_with_temporal_ensemble_pickandplace_v3","group":"so101_follower","episode":"0","predictions":{"RoboJev-27B":0.01008226871633404,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.04,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"taeyoungss/eval_v6_0800002/0","task":"grab the red ball and put it in the box","label":"failure","scored":true,"source":"taeyoungss/eval_v6_0800002","group":"so_follower","episode":"0","predictions":{"RoboJev-27B":0.002895618843390165,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"the-fexy/eval_act_green_cube_in_black_ninety/9","task":"Pick up the orange cylinder and place it into the black container","label":"failure","scored":true,"source":"the-fexy/eval_act_green_cube_in_black_ninety","group":"so101_follower","episode":"9","predictions":{"RoboJev-27B":0.010450126405964542,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"therarelab/eval_act_med_dispense_pickA_combined/4","task":"pick left red bottle or right green bottle","label":"success","scored":true,"source":"therarelab/eval_act_med_dispense_pickA_combined","group":"so100","episode":"4","predictions":{"RoboJev-27B":0.8110310886014386,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.9,"Claude Opus 5.5":0.45,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"therarelab/eval_act_med_dispense_pickA_fixed/0","task":"pick left red bottle or right green bottle","label":"failure","scored":true,"source":"therarelab/eval_act_med_dispense_pickA_fixed","group":"so100","episode":"0","predictions":{"RoboJev-27B":0.7657514471189236,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.04,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.25,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"thomas0829/eval_put_the_doll_into_the_box_adv1_ft_2ep/2","task":"Put the doll into the box.","label":"failure","scored":true,"source":"thomas0829/eval_put_the_doll_into_the_box_adv1_ft_2ep","group":"so100","episode":"2","predictions":{"RoboJev-27B":0.15345747860508727,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.05,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"tinkhireeva/eval_so101_ring_toss/1","task":"Grab the pink ring and put it on black block","label":"failure","scored":true,"source":"tinkhireeva/eval_so101_ring_toss","group":"so101_follower","episode":"1","predictions":{"RoboJev-27B":0.008627695557908701,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"una-auxme/eval_ROS2SmolVLA/63","task":"Pick up the cube and put it in the blue box.","label":"unclear","scored":false,"source":"una-auxme/eval_ROS2SmolVLA","group":"ros2","episode":"63","predictions":{"RoboJev-27B":0.48296324571615296,"GPT-6 Astra":0.84,"GPT-6.1 Sol":0.85,"Claude Opus 5.5":0.6,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"villekuosmanen/eval_27Jan25/27","task":"Pick up the coffee capsules from the table one by one and drop them inside the nearest coffee cup","label":"unclear","scored":false,"source":"villekuosmanen/eval_27Jan25","group":"arx5","episode":"27","predictions":{"RoboJev-27B":0.4853090026322618,"GPT-6 Astra":0.77,"GPT-6.1 Sol":0.78,"Claude Opus 5.5":0.4,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"villekuosmanen/eval_2Feb25_v2/12","task":"Pick up the coffee capsules from the table one by one and drop them inside the nearest coffee cup","label":"success","scored":true,"source":"villekuosmanen/eval_2Feb25_v2","group":"arx5","episode":"12","predictions":{"RoboJev-27B":0.25241155291015543,"GPT-6 Astra":0.95,"GPT-6.1 Sol":0.94,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.68,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"villekuosmanen/eval_busybox_left_toggle_down_10h11m_27-aug-2026/5","task":"Turn the left toggle switch down to \"Off\" position","label":"unclear","scored":false,"source":"villekuosmanen/eval_busybox_left_toggle_down_10h11m_27-aug-2026","group":"so-101","episode":"5","predictions":{"RoboJev-27B":0.3892858245314064,"GPT-6 Astra":0.89,"GPT-6.1 Sol":0.91,"Claude Opus 5.5":0.35,"Claude Sonnet 5.5":0.3,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"villekuosmanen/eval_debug_task_cell_3_15h04m_27-jun-2026/15","task":"Push the Displayport cable into the cable holder on the white block","label":"failure","scored":true,"source":"villekuosmanen/eval_debug_task_cell_3_15h04m_27-jun-2026","group":"so-101","episode":"15","predictions":{"RoboJev-27B":0.003297371311522751,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"villekuosmanen/eval_debug_task_cell_1_16h34m_27-jun-2026/0","task":"Insert the colourful ring into the central wooden peg","label":"success","scored":true,"source":"villekuosmanen/eval_debug_task_cell_1_16h34m_27-jun-2026","group":"so-101","episode":"0","predictions":{"RoboJev-27B":0.9948382526275487,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.93,"Claude Sonnet 5.5":0.93,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"villekuosmanen/eval_push_green_button_merged/158","task":"push the green button","label":"unclear","scored":false,"source":"villekuosmanen/eval_push_green_button_merged","group":"so-101","episode":"158","predictions":{"RoboJev-27B":0.9510439019366512,"GPT-6 Astra":0.88,"GPT-6.1 Sol":0.93,"Claude Opus 5.5":0.2,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"villekuosmanen/eval_insert_colorful_rings/31","task":"Insert the red 'nine' ring into the matching wooden peg","label":"failure","scored":true,"source":"villekuosmanen/eval_insert_colorful_rings","group":"so-101","episode":"31","predictions":{"RoboJev-27B":0.08031105259624365,"GPT-6 Astra":0.04,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.15,"Claude Sonnet 5.5":0.1,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"villekuosmanen/eval_debug_task_cell_8_16h02m_27-jun-2026/13","task":"Fold the brown tea towel","label":"success","scored":true,"source":"villekuosmanen/eval_debug_task_cell_8_16h02m_27-jun-2026","group":"so-101","episode":"13","predictions":{"RoboJev-27B":0.8512406654652304,"GPT-6 Astra":0.18,"GPT-6.1 Sol":0.18,"Claude Opus 5.5":0.5,"Claude Sonnet 5.5":0.12,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"vlasil/eval_smolvla_Put_the_bowl_on_the_plate_random_1108/4","task":"Put the bowl on the plate","label":"failure","scored":true,"source":"vlasil/eval_smolvla_Put_the_bowl_on_the_plate_random_1108","group":"so101_follower","episode":"4","predictions":{"RoboJev-27B":0.005110363102801964,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.02,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"wertania/eval_example_dataset_5/0","task":"Grasp the cube and place it into the box.","label":"failure","scored":true,"source":"wertania/eval_example_dataset_5","group":"so101_follower","episode":"0","predictions":{"RoboJev-27B":0.015009065484223134,"GPT-6 Astra":0.001,"GPT-6.1 Sol":0.001,"Claude Opus 5.5":0.01,"Claude Sonnet 5.5":0.02,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"xsatvik/eval_cube3_xyz_eeobj_test1/8","task":"stack the cubes in the marked area","label":"failure","scored":true,"source":"xsatvik/eval_cube3_xyz_eeobj_test1","group":"so_follower","episode":"8","predictions":{"RoboJev-27B":0.7288632938301538,"GPT-6 Astra":0.03,"GPT-6.1 Sol":0.02,"Claude Opus 5.5":0.3,"Claude Sonnet 5.5":0.5,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"yangxinye/eval_real_so101_record_v1/57","task":"Pick up any purple cube from the white area and place it in cell 2","label":"unclear","scored":false,"source":"yangxinye/eval_real_so101_record_v1","group":"so_follower","episode":"57","predictions":{"RoboJev-27B":0.8450768341722308,"GPT-6 Astra":0.97,"GPT-6.1 Sol":0.98,"Claude Opus 5.5":0.1,"Claude Sonnet 5.5":0.2,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"yeeunleee/eval_rlintern-wettissue-pick_variation_smolvla_test/13","task":"Move wet tissue from left to right","label":"success","scored":true,"source":"yeeunleee/eval_rlintern-wettissue-pick_variation_smolvla_test","group":"so_follower","episode":"13","predictions":{"RoboJev-27B":0.936117569953235,"GPT-6 Astra":0.96,"GPT-6.1 Sol":0.97,"Claude Opus 5.5":0.72,"Claude Sonnet 5.5":0.62,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"yj678/eval_right_pick_place_test_final_v3/0","task":"right arm pick block move and return","label":"unclear","scored":false,"source":"yj678/eval_right_pick_place_test_final_v3","group":"alohamini_client","episode":"0","predictions":{"RoboJev-27B":0.09154499811269315,"GPT-6 Astra":0.01,"GPT-6.1 Sol":0.01,"Claude Opus 5.5":0.03,"Claude Sonnet 5.5":0.03,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}},{"suite":"community","id":"zaringleb/eval_so100_cube_comb_lin_2d_eval_20_40k/14","task":"Grasp a lego block and put it in the bin.","label":"success","scored":true,"source":"zaringleb/eval_so100_cube_comb_lin_2d_eval_20_40k","group":"so100","episode":"14","predictions":{"RoboJev-27B":0.9793136237024173,"GPT-6 Astra":0.99,"GPT-6.1 Sol":0.99,"Claude Opus 5.5":0.95,"Claude Sonnet 5.5":0.96,"JEV-27B-VL":null,"TypeSafe Jev 1.14":null,"Perplexity Decider":null,"Liquid D1":null,"Mercury Decide":null,"Cloudflare Clef":null,"cloudflare/clef-flash":null,"cloudflare/clef-omni":null,"liquid/d1-ultra":null,"open/intern-decision-4b":null,"open/robojev-27b-v1@0.5":null,"open/robojev-27b":null,"open/robojev-4b-v2":null,"open/robojev-4b-v3@0.25":null,"open/robojev-4b-v3@0.5":null,"open/robojev-4b-v3@0.75":null,"open/robojev-4b-v3":null,"openai/gpt-6-luna-decisions":null,"perplexity/pplx-decider-flash-v1.2":null,"respan/span-02":null,"typesafe/jev-1.13":null,"JEV-27B-VL (10 frames)":null,"open/robojev-27b (10 frames)":null,"open/robometer-4b":null}}]