Buckets:

Pranav2748's picture
download
raw
141 kB
{ "dataset": "hotchpotch/S1MB-english-v1@10bcb8c6", "benchmarks": 137, "borda_benchmarks": 137, "cohort": 217, "rescore_check": [ { "model": "5ak3t__scm_max_14b_v0", "benchmarks_checked": 16, "max_abs_diff": 1.1102230246251565e-16 }, { "model": "5ak3t__scm_max_14b_v1", "benchmarks_checked": 16, "max_abs_diff": 4.440892098500626e-16 }, { "model": "5ak3t__scm_mid_4b_v1", "benchmarks_checked": 16, "max_abs_diff": 5.551115123125783e-16 } ], "ours": { "base": { "temps": { "choice": 1.707683209388825, "noul": 2.4105066990845945, "score": 1.2847580560947693 }, "raw": { "adjusted": { "aegis2-noul-test-v1": 0.42052313883299797, "laya--ag-news-choice-test-v1": 0.7910447761194032, "aqua-rat-choice-test-v1": 0.042253521126760604, "arc-choice-test-v1": 0.8823529411764708, "arct-choice-test-v1": 0.2765957446808511, "argument-quality-choice-test-v1": 0.28571428571428575, "argument-quality-noul-test-v1": 0.09289526462740527, "babi-nli-noul-test-v1": 0.10000000000000009, "banking77-choice-test-v1": 0.631578947368421, "bbq-choice-test-v1": 0.8999999999999999, "boardgameqa-choice-test-v1": 0.25000000000000006, "canttalk-noul-test-v1": 0.7200000000000002, "civil-comments-noul-test-v1": 0.3041383169192424, "cladder-noul-test-v1": 0.040000000000000036, "clinc-choice-test-v1": 0.7931034482758621, "contract-nli-choice-test-v1": 0.5173535791757051, "corr2cause-choice-test-v1": 0.0, "creak-noul-test-v1": 0.72, "crows-pairs-choice-test-v1": 0.43749999999999994, "dbpedia-choice-test-v1": 0.9775280898876404, "defeasible-nli-choice-test-v1": 0.41304347826086946, "laya--enron-spam-noul-test-v1": 0.76, "esci-choice-test-v1": 0.0821917808219178, "ethics-choice-test-v1": 0.5000000000000001, "ethics-noul-test-v1": 0.1595238095238094, "ethos-noul-test-v1": 0.45999999999999996, "few-nerd-choice-test-v1": 0.6451612903225806, "fol-nli-choice-test-v1": 0.16393442622950816, "followir-core17-noul-test-v1": 0.26398601398601396, "followir-news21-noul-test-v1": 0.03333333333333344, "followir-robust04-noul-test-v1": 0.4736842105263157, "go-emotions-noul-test-v1": 0.3630486674285902, "gretel-pii-choice-test-v1": 0.6688311688311688, "gsm8k-choice-test-v1": 0.12857142857142861, "hans-noul-test-v1": 0.5, "hatecheck-noul-test-v1": 0.72, "hh-rlhf-choice-test-v1": 0.07692307692307698, "hwu64-choice-test-v1": 0.797872340425532, "impli-noul-test-v1": 0.28, "lexcomp-noul-test-v1": 0.3799999999999999, "logical-entailment-noul-test-v1": 0.040000000000000036, "lonli-choice-test-v1": 0.540983606557377, "massive-choice-test-v1": 0.7806215722120659, "miqa-choice-test-v1": 0.7272727272727273, "mtop-choice-test-v1": 0.74873660804528, "nlsat-noul-test-v1": 0.0, "open-jev--amount-extraction-control-v1-choice-test-v1": 0.5294117647058824, "open-jev--amount-extraction-control-v1-noul-test-v1": 0.0, "open-jev--browser-control-v1-choice-test-v1": 1.0, "open-jev--citation-control-v1-choice-test-v1": 0.6363636363636365, "open-jev--context-retention-control-v1-noul-test-v1": 0.0, "open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391, "open-jev--customer-control-v1-noul-test-v1": 0.75, "open-jev--customer-control-v1-score-test-v1": 0.39788644560460573, "open-jev--drone-control-v1-choice-test-v1": 0.0, "open-jev--drone-control-v1-noul-test-v1": 0.0, "open-jev--drone-control-v1-score-test-v1": 0.0, "open-jev--email-selection-control-v1-choice-test-v1": 0.0, "open-jev--email-selection-control-v1-noul-test-v1": 0.5, "open-jev--entity-alignment-control-v1-noul-test-v1": 0.0, "open-jev--entity-alignment-control-v1-score-test-v1": 0.0, "open-jev--ir-control-v1-choice-test-v1": 0.6799999999999998, "open-jev--ir-control-v1-noul-test-v1": 0.5714285714285714, "open-jev--ir-control-v1-score-test-v1": 0.0, "open-jev--mailroom-control-v1-choice-test-v1": 1.0, "open-jev--mailroom-control-v1-noul-test-v1": 0.7305555555555556, "open-jev--painting-geometry-v1-choice-test-v1": 0.5263157894736842, "open-jev--painting-geometry-v1-noul-test-v1": 0.1333333333333333, "open-jev--painting-geometry-v1-score-test-v1": 0.13055902085337423, "open-jev--phone-extraction-control-v1-choice-test-v1": 0.391304347826087, "open-jev--phone-extraction-control-v1-noul-test-v1": 0.6000000000000001, "open-jev--reasoning-control-v1-choice-test-v1": 0.050000000000000044, "open-jev--reasoning-control-v1-noul-test-v1": 0.05514705882352944, "open-jev--reasoning-control-v1-score-test-v1": 0.17067740907990736, "open-jev--silent-failure-control-v1-noul-test-v1": 0.06000000000000005, "open-jev--snake-v1-choice-test-v1": 0.0, "open-jev--snake-v1-noul-test-v1": 0.0, "open-jev--sponsor-segment-control-v1-choice-test-v1": 0.923076923076923, "open-jev--tic-tac-toe-v1-choice-test-v1": 0.030303030303030165, "open-jev--vizdoom-basic-v1-noul-test-v1": 0.06617647058823528, "open-jev--vizdoom-basic-v1-score-test-v1": 0.1997340624720444, "open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.2027972027972027, "open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.36250536250536247, "open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.02564102564102555, "open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.35811126694717155, "openbookqa-choice-test-v1": 0.7361111111111112, "patent-similarity-score-test-v1": 0.3279628341067954, "paws-noul-test-v1": 0.5800000000000001, "plane-noul-test-v1": 0.0, "poem-sentiment-choice-test-v1": 0.0, "qasper-noul-test-v1": 0.6599999999999999, "quartz-choice-test-v1": 0.47619047619047633, "robust-lr-choice-test-v1": 0.18333333333333332, "ruletaker-noul-test-v1": 0.26, "s1mb-generalization-contextual-choice-choice-test-v1": 0.9484978540772532, "s1mb-generalization-contextual-noul-noul-test-v1": 0.8199999999999998, "s1mb-generalization-contextual-score-score-test-v1": 0.5638258899221804, "s1mb-generalization-diverse-choice-choice-test-v1": 0.86784140969163, "s1mb-generalization-diverse-noul-noul-test-v1": 0.8399999999999999, "s1mb-generalization-diverse-score-score-test-v1": 0.612037228445995, "scicite-choice-test-v1": 0.532258064516129, "scitail-noul-test-v1": 0.8599999999999999, "scone-choice-test-v1": 0.56, "sdoh-nli-noul-test-v1": 0.8999999999999999, "sgd-choice-test-v1": 0.23728813559322043, "snli-choice-test-v1": 0.5967741935483871, "spartqa-choice-test-v1": 0.0, "stepgame-choice-test-v1": 0.25, "synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.1322072402534249, "synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.07273280228740797, "synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.3597289535156989, "synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.2845582024743629, "synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.29607812321130966, "synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.26667314457785307, "synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.18512359296340297, "synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.20288698878246914, "synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.48737468820639496, "synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.3007731311195775, "synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.34625575841540024, "synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.20170169853082132, "synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.4997183632167408, "synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.038876627340836856, "synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.14743786589533547, "synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.1920301308546687, "synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.2508413593010428, "synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.41153895739532786, "synthetic-relevance--nanocoir-noul-test-v1": 0.28739000806659165, "synthetic-relevance--nanocoir-score-test-v1": 0.0, "temporal-nli-choice-test-v1": 0.08064516129032256, "tracie-noul-test-v1": 0.0, "laya--typed-decisions-choice-test-v1": 0.22748534707752452, "laya--typed-decisions-noul-test-v1": 0.3635856680955216, "laya--typed-decisions-score-test-v1": 0.2128120162362931, "ud-ewt-choice-test-v1": 0.18302180685358257, "winobias-choice-test-v1": 0.21739130434782605, "winowhy-noul-test-v1": 0.3999999999999999, "wiqa-choice-test-v1": 0.3015873015873017 }, "noul": 0.3376706817616705, "choice": 0.4570255576401406, "score": 0.21844126619450097, "task_avg": 0.3377125018654374 }, "calibrated": { "adjusted": { "aegis2-noul-test-v1": 0.42052313883299797, "laya--ag-news-choice-test-v1": 0.7910447761194032, "aqua-rat-choice-test-v1": 0.042253521126760604, "arc-choice-test-v1": 0.8823529411764708, "arct-choice-test-v1": 0.2765957446808511, "argument-quality-choice-test-v1": 0.28571428571428575, "argument-quality-noul-test-v1": 0.09289526462740527, "babi-nli-noul-test-v1": 0.10000000000000009, "banking77-choice-test-v1": 0.631578947368421, "bbq-choice-test-v1": 0.8999999999999999, "boardgameqa-choice-test-v1": 0.25000000000000006, "canttalk-noul-test-v1": 0.7200000000000002, "civil-comments-noul-test-v1": 0.3041383169192424, "cladder-noul-test-v1": 0.040000000000000036, "clinc-choice-test-v1": 0.7931034482758621, "contract-nli-choice-test-v1": 0.5173535791757051, "corr2cause-choice-test-v1": 0.0, "creak-noul-test-v1": 0.72, "crows-pairs-choice-test-v1": 0.43749999999999994, "dbpedia-choice-test-v1": 0.9775280898876404, "defeasible-nli-choice-test-v1": 0.41304347826086946, "laya--enron-spam-noul-test-v1": 0.76, "esci-choice-test-v1": 0.0821917808219178, "ethics-choice-test-v1": 0.5000000000000001, "ethics-noul-test-v1": 0.1595238095238094, "ethos-noul-test-v1": 0.45999999999999996, "few-nerd-choice-test-v1": 0.6451612903225806, "fol-nli-choice-test-v1": 0.16393442622950816, "followir-core17-noul-test-v1": 0.26398601398601396, "followir-news21-noul-test-v1": 0.03333333333333344, "followir-robust04-noul-test-v1": 0.4736842105263157, "go-emotions-noul-test-v1": 0.3630486674285902, "gretel-pii-choice-test-v1": 0.6688311688311688, "gsm8k-choice-test-v1": 0.12857142857142861, "hans-noul-test-v1": 0.5, "hatecheck-noul-test-v1": 0.72, "hh-rlhf-choice-test-v1": 0.07692307692307698, "hwu64-choice-test-v1": 0.797872340425532, "impli-noul-test-v1": 0.28, "lexcomp-noul-test-v1": 0.3799999999999999, "logical-entailment-noul-test-v1": 0.040000000000000036, "lonli-choice-test-v1": 0.540983606557377, "massive-choice-test-v1": 0.7806215722120659, "miqa-choice-test-v1": 0.7272727272727273, "mtop-choice-test-v1": 0.74873660804528, "nlsat-noul-test-v1": 0.0, "open-jev--amount-extraction-control-v1-choice-test-v1": 0.5294117647058824, "open-jev--amount-extraction-control-v1-noul-test-v1": 0.0, "open-jev--browser-control-v1-choice-test-v1": 1.0, "open-jev--citation-control-v1-choice-test-v1": 0.6363636363636365, "open-jev--context-retention-control-v1-noul-test-v1": 0.0, "open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391, "open-jev--customer-control-v1-noul-test-v1": 0.75, "open-jev--customer-control-v1-score-test-v1": 0.3893950629833327, "open-jev--drone-control-v1-choice-test-v1": 0.0, "open-jev--drone-control-v1-noul-test-v1": 0.0, "open-jev--drone-control-v1-score-test-v1": 0.0, "open-jev--email-selection-control-v1-choice-test-v1": 0.0, "open-jev--email-selection-control-v1-noul-test-v1": 0.5, "open-jev--entity-alignment-control-v1-noul-test-v1": 0.0, "open-jev--entity-alignment-control-v1-score-test-v1": 0.0, "open-jev--ir-control-v1-choice-test-v1": 0.6799999999999998, "open-jev--ir-control-v1-noul-test-v1": 0.5714285714285714, "open-jev--ir-control-v1-score-test-v1": 0.0, "open-jev--mailroom-control-v1-choice-test-v1": 1.0, "open-jev--mailroom-control-v1-noul-test-v1": 0.7305555555555556, "open-jev--painting-geometry-v1-choice-test-v1": 0.5263157894736842, "open-jev--painting-geometry-v1-noul-test-v1": 0.1333333333333333, "open-jev--painting-geometry-v1-score-test-v1": 0.11001724500712606, "open-jev--phone-extraction-control-v1-choice-test-v1": 0.391304347826087, "open-jev--phone-extraction-control-v1-noul-test-v1": 0.6000000000000001, "open-jev--reasoning-control-v1-choice-test-v1": 0.050000000000000044, "open-jev--reasoning-control-v1-noul-test-v1": 0.05514705882352944, "open-jev--reasoning-control-v1-score-test-v1": 0.12618636261103344, "open-jev--silent-failure-control-v1-noul-test-v1": 0.06000000000000005, "open-jev--snake-v1-choice-test-v1": 0.0, "open-jev--snake-v1-noul-test-v1": 0.0, "open-jev--sponsor-segment-control-v1-choice-test-v1": 0.923076923076923, "open-jev--tic-tac-toe-v1-choice-test-v1": 0.030303030303030165, "open-jev--vizdoom-basic-v1-noul-test-v1": 0.06617647058823528, "open-jev--vizdoom-basic-v1-score-test-v1": 0.1553597082025594, "open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.2027972027972027, "open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.36250536250536247, "open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.02564102564102555, "open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.35811126694717155, "openbookqa-choice-test-v1": 0.7361111111111112, "patent-similarity-score-test-v1": 0.2934810047042089, "paws-noul-test-v1": 0.5800000000000001, "plane-noul-test-v1": 0.0, "poem-sentiment-choice-test-v1": 0.0, "qasper-noul-test-v1": 0.6599999999999999, "quartz-choice-test-v1": 0.47619047619047633, "robust-lr-choice-test-v1": 0.18333333333333332, "ruletaker-noul-test-v1": 0.26, "s1mb-generalization-contextual-choice-choice-test-v1": 0.9484978540772532, "s1mb-generalization-contextual-noul-noul-test-v1": 0.8199999999999998, "s1mb-generalization-contextual-score-score-test-v1": 0.5348292656817324, "s1mb-generalization-diverse-choice-choice-test-v1": 0.86784140969163, "s1mb-generalization-diverse-noul-noul-test-v1": 0.8399999999999999, "s1mb-generalization-diverse-score-score-test-v1": 0.5785965969396042, "scicite-choice-test-v1": 0.532258064516129, "scitail-noul-test-v1": 0.8599999999999999, "scone-choice-test-v1": 0.56, "sdoh-nli-noul-test-v1": 0.8999999999999999, "sgd-choice-test-v1": 0.23728813559322043, "snli-choice-test-v1": 0.5967741935483871, "spartqa-choice-test-v1": 0.0, "stepgame-choice-test-v1": 0.25, "synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.1322072402534249, "synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.009914357195622725, "synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.3597289535156989, "synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.2412115992486591, "synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.29607812321130966, "synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.23325885856088935, "synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.18512359296340297, "synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.10831095033900406, "synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.48737468820639496, "synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.2474660472587129, "synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.34625575841540024, "synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.13921800746762414, "synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.4997183632167408, "synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.14743786589533547, "synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.11267844076262346, "synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.2508413593010428, "synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.40182339219261376, "synthetic-relevance--nanocoir-noul-test-v1": 0.28739000806659165, "synthetic-relevance--nanocoir-score-test-v1": 0.0, "temporal-nli-choice-test-v1": 0.08064516129032256, "tracie-noul-test-v1": 0.0, "laya--typed-decisions-choice-test-v1": 0.22748534707752452, "laya--typed-decisions-noul-test-v1": 0.3635856680955216, "laya--typed-decisions-score-test-v1": 0.28352172500829476, "ud-ewt-choice-test-v1": 0.18302180685358257, "winobias-choice-test-v1": 0.21739130434782605, "winowhy-noul-test-v1": 0.3999999999999999, "wiqa-choice-test-v1": 0.3015873015873017 }, "noul": 0.3376706817616705, "choice": 0.4570255576401406, "score": 0.18882231543636388, "task_avg": 0.3278395182793917 } }, "base_2b": { "temps": { "choice": 4.78807442670338, "noul": 19.999999999982688, "score": 9.956643342471382 }, "raw": { "adjusted": { "aegis2-noul-test-v1": 0.15675873422352282, "laya--ag-news-choice-test-v1": 0.8507462686567167, "aqua-rat-choice-test-v1": 0.0, "arc-choice-test-v1": 0.6323529411764707, "arct-choice-test-v1": 0.34042553191489344, "argument-quality-choice-test-v1": 0.0, "argument-quality-noul-test-v1": 0.0, "babi-nli-noul-test-v1": 0.3799999999999999, "banking77-choice-test-v1": 0.5263157894736842, "bbq-choice-test-v1": 0.4999999999999999, "boardgameqa-choice-test-v1": 0.04687500000000004, "canttalk-noul-test-v1": 0.48, "civil-comments-noul-test-v1": 0.20250058010226324, "cladder-noul-test-v1": 0.0, "clinc-choice-test-v1": 0.6827586206896552, "contract-nli-choice-test-v1": 0.08351409978308025, "corr2cause-choice-test-v1": 0.0, "creak-noul-test-v1": 0.10000000000000009, "crows-pairs-choice-test-v1": 0.14583333333333323, "dbpedia-choice-test-v1": 0.8988764044943821, "defeasible-nli-choice-test-v1": 0.0, "laya--enron-spam-noul-test-v1": 0.08000000000000007, "esci-choice-test-v1": 0.027397260273972553, "ethics-choice-test-v1": 0.0, "ethics-noul-test-v1": 0.22857142857142865, "ethos-noul-test-v1": 0.3999999999999999, "few-nerd-choice-test-v1": 0.5232974910394266, "fol-nli-choice-test-v1": 0.0, "followir-core17-noul-test-v1": 0.2709790209790208, "followir-news21-noul-test-v1": 0.006666666666666599, "followir-robust04-noul-test-v1": 0.4294853154986915, "go-emotions-noul-test-v1": 0.40216633455360284, "gretel-pii-choice-test-v1": 0.4707792207792207, "gsm8k-choice-test-v1": 0.07142857142857141, "hans-noul-test-v1": 0.43999999999999995, "hatecheck-noul-test-v1": 0.3799999999999999, "hh-rlhf-choice-test-v1": 0.07692307692307698, "hwu64-choice-test-v1": 0.5957446808510639, "impli-noul-test-v1": 0.1200000000000001, "lexcomp-noul-test-v1": 0.0, "logical-entailment-noul-test-v1": 0.020000000000000018, "lonli-choice-test-v1": 0.278688524590164, "massive-choice-test-v1": 0.6325411334552102, "miqa-choice-test-v1": 0.6136363636363635, "mtop-choice-test-v1": 0.571710127349909, "nlsat-noul-test-v1": 0.0, "open-jev--amount-extraction-control-v1-choice-test-v1": 0.49019607843137253, "open-jev--amount-extraction-control-v1-noul-test-v1": 0.125, "open-jev--browser-control-v1-choice-test-v1": 0.9782608695652174, "open-jev--citation-control-v1-choice-test-v1": 0.31818181818181823, "open-jev--context-retention-control-v1-noul-test-v1": 0.020000000000000018, "open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391, "open-jev--customer-control-v1-noul-test-v1": 0.5661764705882353, "open-jev--customer-control-v1-score-test-v1": 0.1920571977220239, "open-jev--drone-control-v1-choice-test-v1": 0.0, "open-jev--drone-control-v1-noul-test-v1": 0.0, "open-jev--drone-control-v1-score-test-v1": 0.0, "open-jev--email-selection-control-v1-choice-test-v1": 0.11304347826086972, "open-jev--email-selection-control-v1-noul-test-v1": 0.11538461538461542, "open-jev--entity-alignment-control-v1-noul-test-v1": 0.0, "open-jev--entity-alignment-control-v1-score-test-v1": 0.0, "open-jev--ir-control-v1-choice-test-v1": 0.64, "open-jev--ir-control-v1-noul-test-v1": 0.2142857142857144, "open-jev--ir-control-v1-score-test-v1": 0.0, "open-jev--mailroom-control-v1-choice-test-v1": 0.8333333333333334, "open-jev--mailroom-control-v1-noul-test-v1": 0.5027777777777778, "open-jev--painting-geometry-v1-choice-test-v1": 0.05263157894736847, "open-jev--painting-geometry-v1-noul-test-v1": 0.19999999999999996, "open-jev--painting-geometry-v1-score-test-v1": 0.2059003284578289, "open-jev--phone-extraction-control-v1-choice-test-v1": 0.13043478260869568, "open-jev--phone-extraction-control-v1-noul-test-v1": 0.0, "open-jev--reasoning-control-v1-choice-test-v1": 0.050000000000000044, "open-jev--reasoning-control-v1-noul-test-v1": 0.40441176470588225, "open-jev--reasoning-control-v1-score-test-v1": 0.01836116151128586, "open-jev--silent-failure-control-v1-noul-test-v1": 0.0, "open-jev--snake-v1-choice-test-v1": 0.0, "open-jev--snake-v1-noul-test-v1": 0.03556187766714092, "open-jev--sponsor-segment-control-v1-choice-test-v1": 0.5256410256410257, "open-jev--tic-tac-toe-v1-choice-test-v1": 0.022727272727272582, "open-jev--vizdoom-basic-v1-noul-test-v1": 0.0, "open-jev--vizdoom-basic-v1-score-test-v1": 0.0, "open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.0862470862470861, "open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.5057915057915059, "open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.0, "open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.22907900888265553, "openbookqa-choice-test-v1": 0.25, "patent-similarity-score-test-v1": 0.0, "paws-noul-test-v1": 0.06000000000000005, "plane-noul-test-v1": 0.21999999999999997, "poem-sentiment-choice-test-v1": 0.0, "qasper-noul-test-v1": 0.48, "quartz-choice-test-v1": 0.23809523809523828, "robust-lr-choice-test-v1": 0.0, "ruletaker-noul-test-v1": 0.0, "s1mb-generalization-contextual-choice-choice-test-v1": 0.8326180257510731, "s1mb-generalization-contextual-noul-noul-test-v1": 0.7, "s1mb-generalization-contextual-score-score-test-v1": 0.09813882814177977, "s1mb-generalization-diverse-choice-choice-test-v1": 0.7753303964757708, "s1mb-generalization-diverse-noul-noul-test-v1": 0.45999999999999996, "s1mb-generalization-diverse-score-score-test-v1": 0.24718416049574388, "scicite-choice-test-v1": 0.2580645161290323, "scitail-noul-test-v1": 0.19999999999999996, "scone-choice-test-v1": 0.26, "sdoh-nli-noul-test-v1": 0.15999999999999992, "sgd-choice-test-v1": 0.22033898305084754, "snli-choice-test-v1": 0.16129032258064513, "spartqa-choice-test-v1": 0.0, "stepgame-choice-test-v1": 0.09523809523809523, "synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.25962328735435114, "synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.4192016643984635, "synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.40944448001614253, "synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.32422648339838234, "synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.4970835009297585, "synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.3791955899378503, "synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.5139497440345342, "synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.32055155471466357, "synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.36999631490467055, "synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.0, "synthetic-relevance--nanocoir-noul-test-v1": 0.44900362569846064, "synthetic-relevance--nanocoir-score-test-v1": 0.0, "temporal-nli-choice-test-v1": 0.0, "tracie-noul-test-v1": 0.0, "laya--typed-decisions-choice-test-v1": 0.17588299359671944, "laya--typed-decisions-noul-test-v1": 0.17023925810898288, "laya--typed-decisions-score-test-v1": 0.0, "ud-ewt-choice-test-v1": 0.0, "winobias-choice-test-v1": 0.0, "winowhy-noul-test-v1": 0.0, "wiqa-choice-test-v1": 0.015873015873015886 }, "noul": 0.2287179560241029, "choice": 0.2953177758045324, "score": 0.03626865125374582, "task_avg": 0.186768127694127 }, "calibrated": { "adjusted": { "aegis2-noul-test-v1": 0.15675873422352282, "laya--ag-news-choice-test-v1": 0.8507462686567167, "aqua-rat-choice-test-v1": 0.0, "arc-choice-test-v1": 0.6323529411764707, "arct-choice-test-v1": 0.34042553191489344, "argument-quality-choice-test-v1": 0.0, "argument-quality-noul-test-v1": 0.0, "babi-nli-noul-test-v1": 0.3799999999999999, "banking77-choice-test-v1": 0.5263157894736842, "bbq-choice-test-v1": 0.4999999999999999, "boardgameqa-choice-test-v1": 0.04687500000000004, "canttalk-noul-test-v1": 0.48, "civil-comments-noul-test-v1": 0.20250058010226324, "cladder-noul-test-v1": 0.0, "clinc-choice-test-v1": 0.6827586206896552, "contract-nli-choice-test-v1": 0.08351409978308025, "corr2cause-choice-test-v1": 0.0, "creak-noul-test-v1": 0.10000000000000009, "crows-pairs-choice-test-v1": 0.14583333333333323, "dbpedia-choice-test-v1": 0.8988764044943821, "defeasible-nli-choice-test-v1": 0.0, "laya--enron-spam-noul-test-v1": 0.08000000000000007, "esci-choice-test-v1": 0.027397260273972553, "ethics-choice-test-v1": 0.0, "ethics-noul-test-v1": 0.22857142857142865, "ethos-noul-test-v1": 0.3999999999999999, "few-nerd-choice-test-v1": 0.5232974910394266, "fol-nli-choice-test-v1": 0.0, "followir-core17-noul-test-v1": 0.2709790209790208, "followir-news21-noul-test-v1": 0.006666666666666599, "followir-robust04-noul-test-v1": 0.4294853154986915, "go-emotions-noul-test-v1": 0.40216633455360284, "gretel-pii-choice-test-v1": 0.4707792207792207, "gsm8k-choice-test-v1": 0.07142857142857141, "hans-noul-test-v1": 0.43999999999999995, "hatecheck-noul-test-v1": 0.3799999999999999, "hh-rlhf-choice-test-v1": 0.07692307692307698, "hwu64-choice-test-v1": 0.5957446808510639, "impli-noul-test-v1": 0.1200000000000001, "lexcomp-noul-test-v1": 0.0, "logical-entailment-noul-test-v1": 0.020000000000000018, "lonli-choice-test-v1": 0.278688524590164, "massive-choice-test-v1": 0.6325411334552102, "miqa-choice-test-v1": 0.6136363636363635, "mtop-choice-test-v1": 0.571710127349909, "nlsat-noul-test-v1": 0.0, "open-jev--amount-extraction-control-v1-choice-test-v1": 0.49019607843137253, "open-jev--amount-extraction-control-v1-noul-test-v1": 0.125, "open-jev--browser-control-v1-choice-test-v1": 0.9782608695652174, "open-jev--citation-control-v1-choice-test-v1": 0.31818181818181823, "open-jev--context-retention-control-v1-noul-test-v1": 0.020000000000000018, "open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391, "open-jev--customer-control-v1-noul-test-v1": 0.5661764705882353, "open-jev--customer-control-v1-score-test-v1": 0.02160936177215622, "open-jev--drone-control-v1-choice-test-v1": 0.0, "open-jev--drone-control-v1-noul-test-v1": 0.0, "open-jev--drone-control-v1-score-test-v1": 0.0, "open-jev--email-selection-control-v1-choice-test-v1": 0.11304347826086972, "open-jev--email-selection-control-v1-noul-test-v1": 0.11538461538461542, "open-jev--entity-alignment-control-v1-noul-test-v1": 0.0, "open-jev--entity-alignment-control-v1-score-test-v1": 0.0, "open-jev--ir-control-v1-choice-test-v1": 0.64, "open-jev--ir-control-v1-noul-test-v1": 0.2142857142857144, "open-jev--ir-control-v1-score-test-v1": 0.0, "open-jev--mailroom-control-v1-choice-test-v1": 0.8333333333333334, "open-jev--mailroom-control-v1-noul-test-v1": 0.5027777777777778, "open-jev--painting-geometry-v1-choice-test-v1": 0.05263157894736847, "open-jev--painting-geometry-v1-noul-test-v1": 0.19999999999999996, "open-jev--painting-geometry-v1-score-test-v1": 0.03270065534985134, "open-jev--phone-extraction-control-v1-choice-test-v1": 0.13043478260869568, "open-jev--phone-extraction-control-v1-noul-test-v1": 0.0, "open-jev--reasoning-control-v1-choice-test-v1": 0.050000000000000044, "open-jev--reasoning-control-v1-noul-test-v1": 0.40441176470588225, "open-jev--reasoning-control-v1-score-test-v1": 0.0, "open-jev--silent-failure-control-v1-noul-test-v1": 0.0, "open-jev--snake-v1-choice-test-v1": 0.0, "open-jev--snake-v1-noul-test-v1": 0.03556187766714092, "open-jev--sponsor-segment-control-v1-choice-test-v1": 0.5256410256410257, "open-jev--tic-tac-toe-v1-choice-test-v1": 0.022727272727272582, "open-jev--vizdoom-basic-v1-noul-test-v1": 0.0, "open-jev--vizdoom-basic-v1-score-test-v1": 0.0, "open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.0862470862470861, "open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.5057915057915059, "open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.0, "open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.22907900888265553, "openbookqa-choice-test-v1": 0.25, "patent-similarity-score-test-v1": 0.0, "paws-noul-test-v1": 0.06000000000000005, "plane-noul-test-v1": 0.21999999999999997, "poem-sentiment-choice-test-v1": 0.0, "qasper-noul-test-v1": 0.48, "quartz-choice-test-v1": 0.23809523809523828, "robust-lr-choice-test-v1": 0.0, "ruletaker-noul-test-v1": 0.0, "s1mb-generalization-contextual-choice-choice-test-v1": 0.8326180257510731, "s1mb-generalization-contextual-noul-noul-test-v1": 0.7, "s1mb-generalization-contextual-score-score-test-v1": 0.08664620462166517, "s1mb-generalization-diverse-choice-choice-test-v1": 0.7753303964757708, "s1mb-generalization-diverse-noul-noul-test-v1": 0.45999999999999996, "s1mb-generalization-diverse-score-score-test-v1": 0.1398067606433141, "scicite-choice-test-v1": 0.2580645161290323, "scitail-noul-test-v1": 0.19999999999999996, "scone-choice-test-v1": 0.26, "sdoh-nli-noul-test-v1": 0.15999999999999992, "sgd-choice-test-v1": 0.22033898305084754, "snli-choice-test-v1": 0.16129032258064513, "spartqa-choice-test-v1": 0.0, "stepgame-choice-test-v1": 0.09523809523809523, "synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.25962328735435114, "synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.4192016643984635, "synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.40944448001614253, "synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.32422648339838234, "synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.4970835009297585, "synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.3791955899378503, "synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.5139497440345342, "synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.32055155471466357, "synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.36999631490467055, "synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.04578404341519271, "synthetic-relevance--nanocoir-noul-test-v1": 0.44900362569846064, "synthetic-relevance--nanocoir-score-test-v1": 0.0, "temporal-nli-choice-test-v1": 0.0, "tracie-noul-test-v1": 0.0, "laya--typed-decisions-choice-test-v1": 0.17588299359671944, "laya--typed-decisions-noul-test-v1": 0.17023925810898288, "laya--typed-decisions-score-test-v1": 0.09552482346032742, "ud-ewt-choice-test-v1": 0.0, "winobias-choice-test-v1": 0.0, "winowhy-noul-test-v1": 0.0, "wiqa-choice-test-v1": 0.015873015873015886 }, "noul": 0.2287179560241029, "choice": 0.2953177758045324, "score": 0.020098659488690808, "task_avg": 0.1813781304391087 } }, "rl60": { "temps": { "choice": 1.1599743376333564, "noul": 0.7983784191901301, "score": 0.7276446912498098 }, "raw": { "adjusted": { "aegis2-noul-test-v1": 0.5602707152002926, "laya--ag-news-choice-test-v1": 0.8358208955223883, "aqua-rat-choice-test-v1": 0.21126760563380287, "arc-choice-test-v1": 0.9558823529411764, "arct-choice-test-v1": 0.5319148936170213, "argument-quality-choice-test-v1": 0.6938775510204082, "argument-quality-noul-test-v1": 0.12934047939043625, "babi-nli-noul-test-v1": 0.6400000000000001, "banking77-choice-test-v1": 0.6736842105263157, "bbq-choice-test-v1": 0.9166666666666666, "boardgameqa-choice-test-v1": 0.23437500000000003, "canttalk-noul-test-v1": 0.5800000000000001, "civil-comments-noul-test-v1": 0.2915103139204662, "cladder-noul-test-v1": 0.48, "clinc-choice-test-v1": 0.786206896551724, "contract-nli-choice-test-v1": 0.5466377440347072, "corr2cause-choice-test-v1": 0.11666666666666659, "creak-noul-test-v1": 0.6400000000000001, "crows-pairs-choice-test-v1": 0.6041666666666667, "dbpedia-choice-test-v1": 0.9662921348314606, "defeasible-nli-choice-test-v1": 0.5652173913043479, "laya--enron-spam-noul-test-v1": 0.8999999999999999, "esci-choice-test-v1": 0.2602739726027397, "ethics-choice-test-v1": 0.6666666666666665, "ethics-noul-test-v1": 0.38928571428571423, "ethos-noul-test-v1": 0.6400000000000001, "few-nerd-choice-test-v1": 0.6487455197132617, "fol-nli-choice-test-v1": 0.13114754098360648, "followir-core17-noul-test-v1": 0.29428904428904423, "followir-news21-noul-test-v1": 0.18000000000000016, "followir-robust04-noul-test-v1": 0.7923815062518174, "go-emotions-noul-test-v1": 0.5142817874272971, "gretel-pii-choice-test-v1": 0.7175324675324675, "gsm8k-choice-test-v1": 0.5857142857142857, "hans-noul-test-v1": 0.7000000000000002, "hatecheck-noul-test-v1": 0.6800000000000002, "hh-rlhf-choice-test-v1": 0.05128205128205133, "hwu64-choice-test-v1": 0.7765957446808511, "impli-noul-test-v1": 0.74, "lexcomp-noul-test-v1": 0.43999999999999995, "logical-entailment-noul-test-v1": 0.06000000000000005, "lonli-choice-test-v1": 0.7704918032786885, "massive-choice-test-v1": 0.829981718464351, "miqa-choice-test-v1": 0.9318181818181818, "mtop-choice-test-v1": 0.8001313927632908, "nlsat-noul-test-v1": 0.06000000000000005, "open-jev--amount-extraction-control-v1-choice-test-v1": 0.7254901960784313, "open-jev--amount-extraction-control-v1-noul-test-v1": 0.46875, "open-jev--browser-control-v1-choice-test-v1": 1.0, "open-jev--citation-control-v1-choice-test-v1": 0.9848484848484849, "open-jev--context-retention-control-v1-noul-test-v1": 0.0, "open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391, "open-jev--customer-control-v1-noul-test-v1": 0.47058823529411775, "open-jev--customer-control-v1-score-test-v1": 0.4798837052234861, "open-jev--drone-control-v1-choice-test-v1": 0.0, "open-jev--drone-control-v1-noul-test-v1": 1.0, "open-jev--drone-control-v1-score-test-v1": 0.0, "open-jev--email-selection-control-v1-choice-test-v1": 0.11304347826086972, "open-jev--email-selection-control-v1-noul-test-v1": 0.6153846153846154, "open-jev--entity-alignment-control-v1-noul-test-v1": 0.8333333333333335, "open-jev--entity-alignment-control-v1-score-test-v1": 0.09181388236706145, "open-jev--ir-control-v1-choice-test-v1": 0.84, "open-jev--ir-control-v1-noul-test-v1": 0.8571428571428572, "open-jev--ir-control-v1-score-test-v1": 0.0, "open-jev--mailroom-control-v1-choice-test-v1": 1.0, "open-jev--mailroom-control-v1-noul-test-v1": 0.8111111111111111, "open-jev--painting-geometry-v1-choice-test-v1": 0.8947368421052632, "open-jev--painting-geometry-v1-noul-test-v1": 0.2666666666666666, "open-jev--painting-geometry-v1-score-test-v1": 0.2945765737278052, "open-jev--phone-extraction-control-v1-choice-test-v1": 0.45652173913043476, "open-jev--phone-extraction-control-v1-noul-test-v1": 0.8999999999999999, "open-jev--reasoning-control-v1-choice-test-v1": 0.55, "open-jev--reasoning-control-v1-noul-test-v1": 0.40808823529411775, "open-jev--reasoning-control-v1-score-test-v1": 0.48436402001289314, "open-jev--silent-failure-control-v1-noul-test-v1": 0.6000000000000001, "open-jev--snake-v1-choice-test-v1": 0.0, "open-jev--snake-v1-noul-test-v1": 0.027738264580369876, "open-jev--sponsor-segment-control-v1-choice-test-v1": 1.0, "open-jev--tic-tac-toe-v1-choice-test-v1": 0.03787878787878775, "open-jev--vizdoom-basic-v1-noul-test-v1": 0.7058823529411766, "open-jev--vizdoom-basic-v1-score-test-v1": 0.4617796281661025, "open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.3659673659673659, "open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.5628485628485629, "open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.6801176965111391, "open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.7840112201963534, "openbookqa-choice-test-v1": 0.8611111111111112, "patent-similarity-score-test-v1": 0.3018724918435256, "paws-noul-test-v1": 0.6400000000000001, "plane-noul-test-v1": 0.06000000000000005, "poem-sentiment-choice-test-v1": 0.0, "qasper-noul-test-v1": 0.54, "quartz-choice-test-v1": 0.6428571428571428, "robust-lr-choice-test-v1": 0.65, "ruletaker-noul-test-v1": 0.48, "s1mb-generalization-contextual-choice-choice-test-v1": 0.9613733905579399, "s1mb-generalization-contextual-noul-noul-test-v1": 0.8999999999999999, "s1mb-generalization-contextual-score-score-test-v1": 0.7084916866224619, "s1mb-generalization-diverse-choice-choice-test-v1": 0.9207048458149779, "s1mb-generalization-diverse-noul-noul-test-v1": 0.8799999999999999, "s1mb-generalization-diverse-score-score-test-v1": 0.7178847338130516, "scicite-choice-test-v1": 0.5806451612903225, "scitail-noul-test-v1": 0.6799999999999999, "scone-choice-test-v1": 0.72, "sdoh-nli-noul-test-v1": 0.8199999999999998, "sgd-choice-test-v1": 0.22033898305084754, "snli-choice-test-v1": 0.7096774193548386, "spartqa-choice-test-v1": 0.0967741935483871, "stepgame-choice-test-v1": 0.33333333333333337, "synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.3056378575842238, "synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.19497590804151588, "synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.3978836709428111, "synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.3903572387473163, "synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.44083812096059116, "synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.3280920645399601, "synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.1557554160303185, "synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.31119288161182757, "synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.5616846942591427, "synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.41704488490408065, "synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.3462396114391635, "synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.26812714454978337, "synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.5649185247217279, "synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.26908745017293123, "synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.16736832720824957, "synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.21189142390970628, "synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.4545782796020945, "synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.3189426005270901, "synthetic-relevance--nanocoir-noul-test-v1": 0.512296962815457, "synthetic-relevance--nanocoir-score-test-v1": 0.07479742192783478, "temporal-nli-choice-test-v1": 0.22580645161290325, "tracie-noul-test-v1": 0.18000000000000016, "laya--typed-decisions-choice-test-v1": 0.30864086833403337, "laya--typed-decisions-noul-test-v1": 0.35900076645519086, "laya--typed-decisions-score-test-v1": 0.5457901932960199, "ud-ewt-choice-test-v1": 0.21651090342679127, "winobias-choice-test-v1": 0.5652173913043479, "winowhy-noul-test-v1": 0.3999999999999999, "wiqa-choice-test-v1": 0.3492063492063492 }, "noul": 0.5070371577975563, "choice": 0.5719274044054583, "score": 0.327188854000212, "task_avg": 0.4687178054010756 }, "calibrated": { "adjusted": { "aegis2-noul-test-v1": 0.5602707152002926, "laya--ag-news-choice-test-v1": 0.8358208955223883, "aqua-rat-choice-test-v1": 0.21126760563380287, "arc-choice-test-v1": 0.9558823529411764, "arct-choice-test-v1": 0.5319148936170213, "argument-quality-choice-test-v1": 0.6938775510204082, "argument-quality-noul-test-v1": 0.12934047939043625, "babi-nli-noul-test-v1": 0.6400000000000001, "banking77-choice-test-v1": 0.6736842105263157, "bbq-choice-test-v1": 0.9166666666666666, "boardgameqa-choice-test-v1": 0.23437500000000003, "canttalk-noul-test-v1": 0.5800000000000001, "civil-comments-noul-test-v1": 0.2915103139204662, "cladder-noul-test-v1": 0.48, "clinc-choice-test-v1": 0.786206896551724, "contract-nli-choice-test-v1": 0.5466377440347072, "corr2cause-choice-test-v1": 0.11666666666666659, "creak-noul-test-v1": 0.6400000000000001, "crows-pairs-choice-test-v1": 0.6041666666666667, "dbpedia-choice-test-v1": 0.9662921348314606, "defeasible-nli-choice-test-v1": 0.5652173913043479, "laya--enron-spam-noul-test-v1": 0.8999999999999999, "esci-choice-test-v1": 0.2602739726027397, "ethics-choice-test-v1": 0.6666666666666665, "ethics-noul-test-v1": 0.38928571428571423, "ethos-noul-test-v1": 0.6400000000000001, "few-nerd-choice-test-v1": 0.6487455197132617, "fol-nli-choice-test-v1": 0.13114754098360648, "followir-core17-noul-test-v1": 0.29428904428904423, "followir-news21-noul-test-v1": 0.18000000000000016, "followir-robust04-noul-test-v1": 0.7923815062518174, "go-emotions-noul-test-v1": 0.5142817874272971, "gretel-pii-choice-test-v1": 0.7175324675324675, "gsm8k-choice-test-v1": 0.5857142857142857, "hans-noul-test-v1": 0.7000000000000002, "hatecheck-noul-test-v1": 0.6800000000000002, "hh-rlhf-choice-test-v1": 0.05128205128205133, "hwu64-choice-test-v1": 0.7765957446808511, "impli-noul-test-v1": 0.74, "lexcomp-noul-test-v1": 0.43999999999999995, "logical-entailment-noul-test-v1": 0.06000000000000005, "lonli-choice-test-v1": 0.7704918032786885, "massive-choice-test-v1": 0.829981718464351, "miqa-choice-test-v1": 0.9318181818181818, "mtop-choice-test-v1": 0.8001313927632908, "nlsat-noul-test-v1": 0.06000000000000005, "open-jev--amount-extraction-control-v1-choice-test-v1": 0.7254901960784313, "open-jev--amount-extraction-control-v1-noul-test-v1": 0.46875, "open-jev--browser-control-v1-choice-test-v1": 1.0, "open-jev--citation-control-v1-choice-test-v1": 0.9848484848484849, "open-jev--context-retention-control-v1-noul-test-v1": 0.0, "open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391, "open-jev--customer-control-v1-noul-test-v1": 0.47058823529411775, "open-jev--customer-control-v1-score-test-v1": 0.5010736256437411, "open-jev--drone-control-v1-choice-test-v1": 0.0, "open-jev--drone-control-v1-noul-test-v1": 1.0, "open-jev--drone-control-v1-score-test-v1": 0.0, "open-jev--email-selection-control-v1-choice-test-v1": 0.11304347826086972, "open-jev--email-selection-control-v1-noul-test-v1": 0.6153846153846154, "open-jev--entity-alignment-control-v1-noul-test-v1": 0.8333333333333335, "open-jev--entity-alignment-control-v1-score-test-v1": 0.10768792068745892, "open-jev--ir-control-v1-choice-test-v1": 0.84, "open-jev--ir-control-v1-noul-test-v1": 0.8571428571428572, "open-jev--ir-control-v1-score-test-v1": 0.0, "open-jev--mailroom-control-v1-choice-test-v1": 1.0, "open-jev--mailroom-control-v1-noul-test-v1": 0.8111111111111111, "open-jev--painting-geometry-v1-choice-test-v1": 0.8947368421052632, "open-jev--painting-geometry-v1-noul-test-v1": 0.2666666666666666, "open-jev--painting-geometry-v1-score-test-v1": 0.31163678271733497, "open-jev--phone-extraction-control-v1-choice-test-v1": 0.45652173913043476, "open-jev--phone-extraction-control-v1-noul-test-v1": 0.8999999999999999, "open-jev--reasoning-control-v1-choice-test-v1": 0.55, "open-jev--reasoning-control-v1-noul-test-v1": 0.40808823529411775, "open-jev--reasoning-control-v1-score-test-v1": 0.5116676314844353, "open-jev--silent-failure-control-v1-noul-test-v1": 0.6000000000000001, "open-jev--snake-v1-choice-test-v1": 0.0, "open-jev--snake-v1-noul-test-v1": 0.027738264580369876, "open-jev--sponsor-segment-control-v1-choice-test-v1": 1.0, "open-jev--tic-tac-toe-v1-choice-test-v1": 0.03787878787878775, "open-jev--vizdoom-basic-v1-noul-test-v1": 0.7058823529411766, "open-jev--vizdoom-basic-v1-score-test-v1": 0.5611449747196239, "open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.3659673659673659, "open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.5628485628485629, "open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.6801176965111391, "open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.7840112201963534, "openbookqa-choice-test-v1": 0.8611111111111112, "patent-similarity-score-test-v1": 0.290246823046062, "paws-noul-test-v1": 0.6400000000000001, "plane-noul-test-v1": 0.06000000000000005, "poem-sentiment-choice-test-v1": 0.0, "qasper-noul-test-v1": 0.54, "quartz-choice-test-v1": 0.6428571428571428, "robust-lr-choice-test-v1": 0.65, "ruletaker-noul-test-v1": 0.48, "s1mb-generalization-contextual-choice-choice-test-v1": 0.9613733905579399, "s1mb-generalization-contextual-noul-noul-test-v1": 0.8999999999999999, "s1mb-generalization-contextual-score-score-test-v1": 0.7493735516889689, "s1mb-generalization-diverse-choice-choice-test-v1": 0.9207048458149779, "s1mb-generalization-diverse-noul-noul-test-v1": 0.8799999999999999, "s1mb-generalization-diverse-score-score-test-v1": 0.7605669662438349, "scicite-choice-test-v1": 0.5806451612903225, "scitail-noul-test-v1": 0.6799999999999999, "scone-choice-test-v1": 0.72, "sdoh-nli-noul-test-v1": 0.8199999999999998, "sgd-choice-test-v1": 0.22033898305084754, "snli-choice-test-v1": 0.7096774193548386, "spartqa-choice-test-v1": 0.0967741935483871, "stepgame-choice-test-v1": 0.33333333333333337, "synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.3056378575842238, "synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.24287287966932491, "synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.3978836709428111, "synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.4117364590263355, "synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.44083812096059116, "synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.347061893737288, "synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.1557554160303185, "synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.3533716425449749, "synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.5616846942591427, "synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.4421745077469317, "synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.3462396114391635, "synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.30330704037715905, "synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.5649185247217279, "synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.34563416909402134, "synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.16736832720824957, "synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.2551052742071359, "synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.4545782796020945, "synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.29566497078210885, "synthetic-relevance--nanocoir-noul-test-v1": 0.512296962815457, "synthetic-relevance--nanocoir-score-test-v1": 0.21403263359189162, "temporal-nli-choice-test-v1": 0.22580645161290325, "tracie-noul-test-v1": 0.18000000000000016, "laya--typed-decisions-choice-test-v1": 0.30864086833403337, "laya--typed-decisions-noul-test-v1": 0.35900076645519086, "laya--typed-decisions-score-test-v1": 0.5067348569558621, "ud-ewt-choice-test-v1": 0.21651090342679127, "winobias-choice-test-v1": 0.5652173913043479, "winowhy-noul-test-v1": 0.3999999999999999, "wiqa-choice-test-v1": 0.3492063492063492 }, "noul": 0.5070371577975563, "choice": 0.5719274044054583, "score": 0.3576711716173568, "task_avg": 0.47887857794012384 } }, "rl60_routed30": { "temps": null, "raw": { "adjusted": { "aegis2-noul-test-v1": 0.5754527162977867, "laya--ag-news-choice-test-v1": 0.8507462686567167, "aqua-rat-choice-test-v1": 0.6619718309859156, "arc-choice-test-v1": 0.9852941176470588, "arct-choice-test-v1": 0.7446808510638298, "argument-quality-choice-test-v1": 0.7755102040816326, "argument-quality-noul-test-v1": 0.09000837414976615, "babi-nli-noul-test-v1": 0.8, "banking77-choice-test-v1": 0.7157894736842105, "bbq-choice-test-v1": 0.95, "boardgameqa-choice-test-v1": 0.65625, "canttalk-noul-test-v1": 0.6400000000000001, "civil-comments-noul-test-v1": 0.312200496400324, "cladder-noul-test-v1": 0.6200000000000001, "clinc-choice-test-v1": 0.8896551724137931, "contract-nli-choice-test-v1": 0.6052060737527115, "corr2cause-choice-test-v1": 0.23333333333333336, "creak-noul-test-v1": 0.7200000000000002, "crows-pairs-choice-test-v1": 0.6874999999999999, "dbpedia-choice-test-v1": 0.9662921348314606, "defeasible-nli-choice-test-v1": 0.6956521739130435, "laya--enron-spam-noul-test-v1": 0.8999999999999999, "esci-choice-test-v1": 0.2328767123287671, "ethics-choice-test-v1": 0.3333333333333334, "ethics-noul-test-v1": 0.5571428571428569, "ethos-noul-test-v1": 0.7, "few-nerd-choice-test-v1": 0.7025089605734768, "fol-nli-choice-test-v1": 0.540983606557377, "followir-core17-noul-test-v1": 0.3665501165501166, "followir-news21-noul-test-v1": 0.2466666666666666, "followir-robust04-noul-test-v1": 0.7813317824949113, "go-emotions-noul-test-v1": 0.5453700644558837, "gretel-pii-choice-test-v1": 0.8051948051948051, "gsm8k-choice-test-v1": 0.9428571428571428, "hans-noul-test-v1": 0.76, "hatecheck-noul-test-v1": 0.72, "hh-rlhf-choice-test-v1": 0.0, "hwu64-choice-test-v1": 0.8404255319148937, "impli-noul-test-v1": 0.78, "lexcomp-noul-test-v1": 0.43999999999999995, "logical-entailment-noul-test-v1": 0.6800000000000002, "lonli-choice-test-v1": 0.8360655737704918, "massive-choice-test-v1": 0.8409506398537477, "miqa-choice-test-v1": 0.8636363636363635, "mtop-choice-test-v1": 0.8172629876692945, "nlsat-noul-test-v1": 0.1200000000000001, "open-jev--amount-extraction-control-v1-choice-test-v1": 0.7254901960784313, "open-jev--amount-extraction-control-v1-noul-test-v1": 0.53125, "open-jev--browser-control-v1-choice-test-v1": 1.0, "open-jev--citation-control-v1-choice-test-v1": 0.9545454545454545, "open-jev--context-retention-control-v1-noul-test-v1": 0.0, "open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391, "open-jev--customer-control-v1-noul-test-v1": 0.47058823529411775, "open-jev--customer-control-v1-score-test-v1": 0.4999230199817669, "open-jev--drone-control-v1-choice-test-v1": 0.34210526315789475, "open-jev--drone-control-v1-noul-test-v1": 1.0, "open-jev--drone-control-v1-score-test-v1": 0.0, "open-jev--email-selection-control-v1-choice-test-v1": 0.3217391304347826, "open-jev--email-selection-control-v1-noul-test-v1": 0.6923076923076925, "open-jev--entity-alignment-control-v1-noul-test-v1": 0.9444444444444444, "open-jev--entity-alignment-control-v1-score-test-v1": 0.21129200822082306, "open-jev--ir-control-v1-choice-test-v1": 0.84, "open-jev--ir-control-v1-noul-test-v1": 0.9285714285714286, "open-jev--ir-control-v1-score-test-v1": 0.24326190557901484, "open-jev--mailroom-control-v1-choice-test-v1": 1.0, "open-jev--mailroom-control-v1-noul-test-v1": 0.8111111111111111, "open-jev--painting-geometry-v1-choice-test-v1": 0.8947368421052632, "open-jev--painting-geometry-v1-noul-test-v1": 0.2666666666666666, "open-jev--painting-geometry-v1-score-test-v1": 0.5976683560167559, "open-jev--phone-extraction-control-v1-choice-test-v1": 0.5434782608695653, "open-jev--phone-extraction-control-v1-noul-test-v1": 0.8999999999999999, "open-jev--reasoning-control-v1-choice-test-v1": 0.7000000000000001, "open-jev--reasoning-control-v1-noul-test-v1": 0.5845588235294117, "open-jev--reasoning-control-v1-score-test-v1": 0.7667997990055253, "open-jev--silent-failure-control-v1-noul-test-v1": 0.6600000000000001, "open-jev--snake-v1-choice-test-v1": 0.154639175257732, "open-jev--snake-v1-noul-test-v1": 0.8918918918918919, "open-jev--sponsor-segment-control-v1-choice-test-v1": 0.9487179487179487, "open-jev--tic-tac-toe-v1-choice-test-v1": 0.5454545454545453, "open-jev--vizdoom-basic-v1-noul-test-v1": 0.8823529411764706, "open-jev--vizdoom-basic-v1-score-test-v1": 0.7063524968418744, "open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.3659673659673659, "open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.6598026598026596, "open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.8226145439260193, "open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.7260402057035997, "openbookqa-choice-test-v1": 0.888888888888889, "patent-similarity-score-test-v1": 0.37933688115458797, "paws-noul-test-v1": 0.7, "plane-noul-test-v1": 0.08000000000000007, "poem-sentiment-choice-test-v1": 0.0, "qasper-noul-test-v1": 0.6200000000000001, "quartz-choice-test-v1": 0.7142857142857143, "robust-lr-choice-test-v1": 0.7, "ruletaker-noul-test-v1": 0.6599999999999999, "s1mb-generalization-contextual-choice-choice-test-v1": 1.0, "s1mb-generalization-contextual-noul-noul-test-v1": 0.94, "s1mb-generalization-contextual-score-score-test-v1": 0.8558560747528754, "s1mb-generalization-diverse-choice-choice-test-v1": 0.9471365638766519, "s1mb-generalization-diverse-noul-noul-test-v1": 0.9199999999999999, "s1mb-generalization-diverse-score-score-test-v1": 0.849707901053516, "scicite-choice-test-v1": 0.5967741935483871, "scitail-noul-test-v1": 0.76, "scone-choice-test-v1": 0.98, "sdoh-nli-noul-test-v1": 0.8399999999999999, "sgd-choice-test-v1": 0.30508474576271183, "snli-choice-test-v1": 0.7096774193548386, "spartqa-choice-test-v1": 0.532258064516129, "stepgame-choice-test-v1": 0.488095238095238, "synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.4134112329279427, "synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.14842430453822486, "synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.3902108553958745, "synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.42357205529278996, "synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.4472720711071787, "synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.25044390721168586, "synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.2594264381469542, "synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.4839618133977178, "synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.5663302744040744, "synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.338247053950411, "synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.3508253526903282, "synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.2566050750253225, "synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.5853724999543066, "synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.29342713634055395, "synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.24720904201048044, "synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.2761282715556823, "synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.442376047517552, "synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.18507053455759748, "synthetic-relevance--nanocoir-noul-test-v1": 0.6313993273825997, "synthetic-relevance--nanocoir-score-test-v1": 0.0827347435762017, "temporal-nli-choice-test-v1": 0.7580645161290323, "tracie-noul-test-v1": 0.26, "laya--typed-decisions-choice-test-v1": 0.2767724141428169, "laya--typed-decisions-noul-test-v1": 0.4353576361529514, "laya--typed-decisions-score-test-v1": 0.504422923959694, "ud-ewt-choice-test-v1": 0.6308411214953271, "winobias-choice-test-v1": 0.717391304347826, "winowhy-noul-test-v1": 0.3400000000000001, "wiqa-choice-test-v1": 0.33333333333333326 }, "noul": 0.5827471502074819, "choice": 0.6763083260170817, "score": 0.39777315533393437, "task_avg": 0.5522762105194993 } }, "v1_joint": { "temps": { "choice": 1.2843740495491411, "noul": 1.1776347713530488, "score": 1.0535480782391846 }, "raw": { "adjusted": { "aegis2-noul-test-v1": 0.4433875983171758, "laya--ag-news-choice-test-v1": 0.7910447761194032, "aqua-rat-choice-test-v1": 0.028169014084507067, "arc-choice-test-v1": 0.9705882352941176, "arct-choice-test-v1": 0.48936170212765956, "argument-quality-choice-test-v1": 0.6326530612244897, "argument-quality-noul-test-v1": 0.11079818480422476, "babi-nli-noul-test-v1": 0.41999999999999993, "banking77-choice-test-v1": 0.6631578947368422, "bbq-choice-test-v1": 0.95, "boardgameqa-choice-test-v1": 0.375, "canttalk-noul-test-v1": 0.72, "civil-comments-noul-test-v1": 0.314524306059917, "cladder-noul-test-v1": 0.26, "clinc-choice-test-v1": 0.8275862068965518, "contract-nli-choice-test-v1": 0.6106290672451193, "corr2cause-choice-test-v1": 0.0, "creak-noul-test-v1": 0.74, "crows-pairs-choice-test-v1": 0.5416666666666667, "dbpedia-choice-test-v1": 0.9775280898876404, "defeasible-nli-choice-test-v1": 0.41304347826086946, "laya--enron-spam-noul-test-v1": 0.8999999999999999, "esci-choice-test-v1": 0.17808219178082194, "ethics-choice-test-v1": 0.3333333333333334, "ethics-noul-test-v1": 0.43452380952380953, "ethos-noul-test-v1": 0.72, "few-nerd-choice-test-v1": 0.6093189964157706, "fol-nli-choice-test-v1": 0.11475409836065575, "followir-core17-noul-test-v1": 0.35897435897435903, "followir-news21-noul-test-v1": 0.2333333333333334, "followir-robust04-noul-test-v1": 0.8200058156440826, "go-emotions-noul-test-v1": 0.48444169078029087, "gretel-pii-choice-test-v1": 0.7727272727272728, "gsm8k-choice-test-v1": 0.24285714285714285, "hans-noul-test-v1": 0.7000000000000002, "hatecheck-noul-test-v1": 0.7799999999999998, "hh-rlhf-choice-test-v1": 0.10256410256410266, "hwu64-choice-test-v1": 0.797872340425532, "impli-noul-test-v1": 0.54, "lexcomp-noul-test-v1": 0.3999999999999999, "logical-entailment-noul-test-v1": 0.20000000000000018, "lonli-choice-test-v1": 0.6229508196721312, "massive-choice-test-v1": 0.8244972577696527, "miqa-choice-test-v1": 0.8181818181818182, "mtop-choice-test-v1": 0.7772892662219527, "nlsat-noul-test-v1": 0.0, "open-jev--amount-extraction-control-v1-choice-test-v1": 0.7254901960784313, "open-jev--amount-extraction-control-v1-noul-test-v1": 0.6875, "open-jev--browser-control-v1-choice-test-v1": 0.6086956521739129, "open-jev--citation-control-v1-choice-test-v1": 0.7121212121212123, "open-jev--context-retention-control-v1-noul-test-v1": 0.06000000000000005, "open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391, "open-jev--customer-control-v1-noul-test-v1": 1.0, "open-jev--customer-control-v1-score-test-v1": 0.4592296552398998, "open-jev--drone-control-v1-choice-test-v1": 0.0, "open-jev--drone-control-v1-noul-test-v1": 0.9411764705882353, "open-jev--drone-control-v1-score-test-v1": 0.0, "open-jev--email-selection-control-v1-choice-test-v1": 0.37391304347826093, "open-jev--email-selection-control-v1-noul-test-v1": 0.42307692307692313, "open-jev--entity-alignment-control-v1-noul-test-v1": 0.7115384615384615, "open-jev--entity-alignment-control-v1-score-test-v1": 0.10561298468116609, "open-jev--ir-control-v1-choice-test-v1": 0.6799999999999998, "open-jev--ir-control-v1-noul-test-v1": 0.7857142857142856, "open-jev--ir-control-v1-score-test-v1": 0.0, "open-jev--mailroom-control-v1-choice-test-v1": 1.0, "open-jev--mailroom-control-v1-noul-test-v1": 0.7722222222222221, "open-jev--painting-geometry-v1-choice-test-v1": 0.47368421052631576, "open-jev--painting-geometry-v1-noul-test-v1": 0.06666666666666665, "open-jev--painting-geometry-v1-score-test-v1": 0.0, "open-jev--phone-extraction-control-v1-choice-test-v1": 0.6739130434782609, "open-jev--phone-extraction-control-v1-noul-test-v1": 0.9090909090909092, "open-jev--reasoning-control-v1-choice-test-v1": 0.55, "open-jev--reasoning-control-v1-noul-test-v1": 0.4007352941176472, "open-jev--reasoning-control-v1-score-test-v1": 0.4748872860767298, "open-jev--silent-failure-control-v1-noul-test-v1": 0.72, "open-jev--snake-v1-choice-test-v1": 0.18556701030927833, "open-jev--snake-v1-noul-test-v1": 0.1813655761024182, "open-jev--sponsor-segment-control-v1-choice-test-v1": 0.9487179487179487, "open-jev--tic-tac-toe-v1-choice-test-v1": 0.0, "open-jev--vizdoom-basic-v1-noul-test-v1": 0.8235294117647058, "open-jev--vizdoom-basic-v1-score-test-v1": 0.4303267488828373, "open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.3543123543123543, "open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.5851565851565852, "open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.7057587221521646, "open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.5409069658719026, "openbookqa-choice-test-v1": 0.7638888888888888, "patent-similarity-score-test-v1": 0.3330279158835684, "paws-noul-test-v1": 0.6400000000000001, "plane-noul-test-v1": 0.1200000000000001, "poem-sentiment-choice-test-v1": 0.0, "qasper-noul-test-v1": 0.6400000000000001, "quartz-choice-test-v1": 0.7142857142857143, "robust-lr-choice-test-v1": 0.3166666666666666, "ruletaker-noul-test-v1": 0.3600000000000001, "s1mb-generalization-contextual-choice-choice-test-v1": 0.9613733905579399, "s1mb-generalization-contextual-noul-noul-test-v1": 0.8799999999999999, "s1mb-generalization-contextual-score-score-test-v1": 0.624034874401848, "s1mb-generalization-diverse-choice-choice-test-v1": 0.881057268722467, "s1mb-generalization-diverse-noul-noul-test-v1": 0.8799999999999999, "s1mb-generalization-diverse-score-score-test-v1": 0.7195231998977583, "scicite-choice-test-v1": 0.4999999999999999, "scitail-noul-test-v1": 0.6799999999999999, "scone-choice-test-v1": 0.54, "sdoh-nli-noul-test-v1": 0.8399999999999999, "sgd-choice-test-v1": 0.2542372881355933, "snli-choice-test-v1": 0.6612903225806452, "spartqa-choice-test-v1": 0.0967741935483871, "stepgame-choice-test-v1": 0.27380952380952384, "synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.19926157464108507, "synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.12693432570770635, "synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.41770258066944344, "synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.37295431133360935, "synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.39002621310810626, "synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.34722306717996154, "synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.15598167317155953, "synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.17705811713353992, "synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.5384503681124295, "synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.4019849723419704, "synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.3663022294130087, "synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.22829536601785572, "synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.5156445494559176, "synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.2591265118565217, "synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.17144951511129158, "synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.16315568062226238, "synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.32832924999283186, "synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.40920848113560715, "synthetic-relevance--nanocoir-noul-test-v1": 0.4870635794503144, "synthetic-relevance--nanocoir-score-test-v1": 0.0, "temporal-nli-choice-test-v1": 0.24193548387096778, "tracie-noul-test-v1": 0.0, "laya--typed-decisions-choice-test-v1": 0.3138313776226675, "laya--typed-decisions-noul-test-v1": 0.3480258402550176, "laya--typed-decisions-score-test-v1": 0.40457483081738554, "ud-ewt-choice-test-v1": 0.29595015576323985, "winobias-choice-test-v1": 0.41304347826086946, "winowhy-noul-test-v1": 0.3400000000000001, "wiqa-choice-test-v1": 0.36507936507936506 }, "noul": 0.5007962257490454, "choice": 0.5230924425272342, "score": 0.2874837299623918, "task_avg": 0.4371241327462238 }, "calibrated": { "adjusted": { "aegis2-noul-test-v1": 0.4433875983171758, "laya--ag-news-choice-test-v1": 0.7910447761194032, "aqua-rat-choice-test-v1": 0.028169014084507067, "arc-choice-test-v1": 0.9705882352941176, "arct-choice-test-v1": 0.48936170212765956, "argument-quality-choice-test-v1": 0.6326530612244897, "argument-quality-noul-test-v1": 0.11079818480422476, "babi-nli-noul-test-v1": 0.41999999999999993, "banking77-choice-test-v1": 0.6631578947368422, "bbq-choice-test-v1": 0.95, "boardgameqa-choice-test-v1": 0.375, "canttalk-noul-test-v1": 0.72, "civil-comments-noul-test-v1": 0.314524306059917, "cladder-noul-test-v1": 0.26, "clinc-choice-test-v1": 0.8275862068965518, "contract-nli-choice-test-v1": 0.6106290672451193, "corr2cause-choice-test-v1": 0.0, "creak-noul-test-v1": 0.74, "crows-pairs-choice-test-v1": 0.5416666666666667, "dbpedia-choice-test-v1": 0.9775280898876404, "defeasible-nli-choice-test-v1": 0.41304347826086946, "laya--enron-spam-noul-test-v1": 0.8999999999999999, "esci-choice-test-v1": 0.17808219178082194, "ethics-choice-test-v1": 0.3333333333333334, "ethics-noul-test-v1": 0.43452380952380953, "ethos-noul-test-v1": 0.72, "few-nerd-choice-test-v1": 0.6093189964157706, "fol-nli-choice-test-v1": 0.11475409836065575, "followir-core17-noul-test-v1": 0.35897435897435903, "followir-news21-noul-test-v1": 0.2333333333333334, "followir-robust04-noul-test-v1": 0.8200058156440826, "go-emotions-noul-test-v1": 0.48444169078029087, "gretel-pii-choice-test-v1": 0.7727272727272728, "gsm8k-choice-test-v1": 0.24285714285714285, "hans-noul-test-v1": 0.7000000000000002, "hatecheck-noul-test-v1": 0.7799999999999998, "hh-rlhf-choice-test-v1": 0.10256410256410266, "hwu64-choice-test-v1": 0.797872340425532, "impli-noul-test-v1": 0.54, "lexcomp-noul-test-v1": 0.3999999999999999, "logical-entailment-noul-test-v1": 0.20000000000000018, "lonli-choice-test-v1": 0.6229508196721312, "massive-choice-test-v1": 0.8244972577696527, "miqa-choice-test-v1": 0.8181818181818182, "mtop-choice-test-v1": 0.7772892662219527, "nlsat-noul-test-v1": 0.0, "open-jev--amount-extraction-control-v1-choice-test-v1": 0.7254901960784313, "open-jev--amount-extraction-control-v1-noul-test-v1": 0.6875, "open-jev--browser-control-v1-choice-test-v1": 0.6086956521739129, "open-jev--citation-control-v1-choice-test-v1": 0.7121212121212123, "open-jev--context-retention-control-v1-noul-test-v1": 0.06000000000000005, "open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391, "open-jev--customer-control-v1-noul-test-v1": 1.0, "open-jev--customer-control-v1-score-test-v1": 0.4550389617256263, "open-jev--drone-control-v1-choice-test-v1": 0.0, "open-jev--drone-control-v1-noul-test-v1": 0.9411764705882353, "open-jev--drone-control-v1-score-test-v1": 0.0, "open-jev--email-selection-control-v1-choice-test-v1": 0.37391304347826093, "open-jev--email-selection-control-v1-noul-test-v1": 0.42307692307692313, "open-jev--entity-alignment-control-v1-noul-test-v1": 0.7115384615384615, "open-jev--entity-alignment-control-v1-score-test-v1": 0.10354883642807688, "open-jev--ir-control-v1-choice-test-v1": 0.6799999999999998, "open-jev--ir-control-v1-noul-test-v1": 0.7857142857142856, "open-jev--ir-control-v1-score-test-v1": 0.0, "open-jev--mailroom-control-v1-choice-test-v1": 1.0, "open-jev--mailroom-control-v1-noul-test-v1": 0.7722222222222221, "open-jev--painting-geometry-v1-choice-test-v1": 0.47368421052631576, "open-jev--painting-geometry-v1-noul-test-v1": 0.06666666666666665, "open-jev--painting-geometry-v1-score-test-v1": 0.0, "open-jev--phone-extraction-control-v1-choice-test-v1": 0.6739130434782609, "open-jev--phone-extraction-control-v1-noul-test-v1": 0.9090909090909092, "open-jev--reasoning-control-v1-choice-test-v1": 0.55, "open-jev--reasoning-control-v1-noul-test-v1": 0.4007352941176472, "open-jev--reasoning-control-v1-score-test-v1": 0.46228880266144246, "open-jev--silent-failure-control-v1-noul-test-v1": 0.72, "open-jev--snake-v1-choice-test-v1": 0.18556701030927833, "open-jev--snake-v1-noul-test-v1": 0.1813655761024182, "open-jev--sponsor-segment-control-v1-choice-test-v1": 0.9487179487179487, "open-jev--tic-tac-toe-v1-choice-test-v1": 0.0, "open-jev--vizdoom-basic-v1-noul-test-v1": 0.8235294117647058, "open-jev--vizdoom-basic-v1-score-test-v1": 0.4189118599502557, "open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.3543123543123543, "open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.5851565851565852, "open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.7057587221521646, "open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.5409069658719026, "openbookqa-choice-test-v1": 0.7638888888888888, "patent-similarity-score-test-v1": 0.3266830724535009, "paws-noul-test-v1": 0.6400000000000001, "plane-noul-test-v1": 0.1200000000000001, "poem-sentiment-choice-test-v1": 0.0, "qasper-noul-test-v1": 0.6400000000000001, "quartz-choice-test-v1": 0.7142857142857143, "robust-lr-choice-test-v1": 0.3166666666666666, "ruletaker-noul-test-v1": 0.3600000000000001, "s1mb-generalization-contextual-choice-choice-test-v1": 0.9613733905579399, "s1mb-generalization-contextual-noul-noul-test-v1": 0.8799999999999999, "s1mb-generalization-contextual-score-score-test-v1": 0.6149834321085637, "s1mb-generalization-diverse-choice-choice-test-v1": 0.881057268722467, "s1mb-generalization-diverse-noul-noul-test-v1": 0.8799999999999999, "s1mb-generalization-diverse-score-score-test-v1": 0.7096966733728995, "scicite-choice-test-v1": 0.4999999999999999, "scitail-noul-test-v1": 0.6799999999999999, "scone-choice-test-v1": 0.54, "sdoh-nli-noul-test-v1": 0.8399999999999999, "sgd-choice-test-v1": 0.2542372881355933, "snli-choice-test-v1": 0.6612903225806452, "spartqa-choice-test-v1": 0.0967741935483871, "stepgame-choice-test-v1": 0.27380952380952384, "synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.19926157464108507, "synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.11167728663667009, "synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.41770258066944344, "synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.3649886179620183, "synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.39002621310810626, "synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.34097038999966456, "synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.15598167317155953, "synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.15821570935090346, "synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.5384503681124295, "synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.39363766129605826, "synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.3663022294130087, "synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.21236216453239287, "synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.5156445494559176, "synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.229478884673753, "synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.17144951511129158, "synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.14839491556145668, "synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.32832924999283186, "synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.4100041834166628, "synthetic-relevance--nanocoir-noul-test-v1": 0.4870635794503144, "synthetic-relevance--nanocoir-score-test-v1": 0.0, "temporal-nli-choice-test-v1": 0.24193548387096778, "tracie-noul-test-v1": 0.0, "laya--typed-decisions-choice-test-v1": 0.3138313776226675, "laya--typed-decisions-noul-test-v1": 0.3480258402550176, "laya--typed-decisions-score-test-v1": 0.41387338748058744, "ud-ewt-choice-test-v1": 0.29595015576323985, "winobias-choice-test-v1": 0.41304347826086946, "winowhy-noul-test-v1": 0.3400000000000001, "wiqa-choice-test-v1": 0.36507936507936506 }, "noul": 0.5007962257490454, "choice": 0.5230924425272342, "score": 0.27975023045764447, "task_avg": 0.4345462995779747 } }, "v2_2b_ro": { "temps": { "choice": 1.0772703967295125, "noul": 0.6149937401183327, "score": 0.7973321069676444 }, "raw": { "adjusted": { "aegis2-noul-test-v1": 0.44539967075178355, "laya--ag-news-choice-test-v1": 0.8656716417910449, "aqua-rat-choice-test-v1": 0.042253521126760604, "arc-choice-test-v1": 0.7205882352941178, "arct-choice-test-v1": 0.17021276595744672, "argument-quality-choice-test-v1": 0.673469387755102, "argument-quality-noul-test-v1": 0.13869566972747505, "babi-nli-noul-test-v1": 0.6200000000000001, "banking77-choice-test-v1": 0.6105263157894737, "bbq-choice-test-v1": 0.7666666666666666, "boardgameqa-choice-test-v1": 0.09375, "canttalk-noul-test-v1": 0.6400000000000001, "civil-comments-noul-test-v1": 0.20946003197816698, "cladder-noul-test-v1": 0.020000000000000018, "clinc-choice-test-v1": 0.7724137931034483, "contract-nli-choice-test-v1": 0.4511930585683298, "corr2cause-choice-test-v1": 0.0, "creak-noul-test-v1": 0.48, "crows-pairs-choice-test-v1": 0.27083333333333337, "dbpedia-choice-test-v1": 0.9550561797752809, "defeasible-nli-choice-test-v1": 0.19565217391304343, "laya--enron-spam-noul-test-v1": 0.74, "esci-choice-test-v1": 0.17808219178082194, "ethics-choice-test-v1": 0.6666666666666665, "ethics-noul-test-v1": 0.3321428571428571, "ethos-noul-test-v1": 0.6200000000000001, "few-nerd-choice-test-v1": 0.5878136200716847, "fol-nli-choice-test-v1": 0.14754098360655732, "followir-core17-noul-test-v1": 0.3152680652680653, "followir-news21-noul-test-v1": 0.3799999999999999, "followir-robust04-noul-test-v1": 0.7176504797906369, "go-emotions-noul-test-v1": 0.4876902085539958, "gretel-pii-choice-test-v1": 0.6753246753246753, "gsm8k-choice-test-v1": 0.15714285714285714, "hans-noul-test-v1": 0.48, "hatecheck-noul-test-v1": 0.52, "hh-rlhf-choice-test-v1": 0.0, "hwu64-choice-test-v1": 0.7659574468085106, "impli-noul-test-v1": 0.54, "lexcomp-noul-test-v1": 0.3599999999999999, "logical-entailment-noul-test-v1": 0.1399999999999999, "lonli-choice-test-v1": 0.6229508196721312, "massive-choice-test-v1": 0.7477148080438757, "miqa-choice-test-v1": 0.7727272727272727, "mtop-choice-test-v1": 0.7144734182332727, "nlsat-noul-test-v1": 0.0, "open-jev--amount-extraction-control-v1-choice-test-v1": 0.7254901960784313, "open-jev--amount-extraction-control-v1-noul-test-v1": 0.15625, "open-jev--browser-control-v1-choice-test-v1": 0.6086956521739129, "open-jev--citation-control-v1-choice-test-v1": 0.7272727272727273, "open-jev--context-retention-control-v1-noul-test-v1": 0.0, "open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391, "open-jev--customer-control-v1-noul-test-v1": 0.8198529411764706, "open-jev--customer-control-v1-score-test-v1": 0.37576589136321537, "open-jev--drone-control-v1-choice-test-v1": 0.0, "open-jev--drone-control-v1-noul-test-v1": 0.9411764705882353, "open-jev--drone-control-v1-score-test-v1": 0.0, "open-jev--email-selection-control-v1-choice-test-v1": 0.21739130434782614, "open-jev--email-selection-control-v1-noul-test-v1": 0.6153846153846154, "open-jev--entity-alignment-control-v1-noul-test-v1": 0.3632478632478633, "open-jev--entity-alignment-control-v1-score-test-v1": 0.0, "open-jev--ir-control-v1-choice-test-v1": 0.7999999999999998, "open-jev--ir-control-v1-noul-test-v1": 0.7857142857142856, "open-jev--ir-control-v1-score-test-v1": 0.0, "open-jev--mailroom-control-v1-choice-test-v1": 0.9166666666666667, "open-jev--mailroom-control-v1-noul-test-v1": 0.786111111111111, "open-jev--painting-geometry-v1-choice-test-v1": 0.5263157894736842, "open-jev--painting-geometry-v1-noul-test-v1": 0.4761904761904763, "open-jev--painting-geometry-v1-score-test-v1": 0.0, "open-jev--phone-extraction-control-v1-choice-test-v1": 0.5217391304347825, "open-jev--phone-extraction-control-v1-noul-test-v1": 0.30000000000000004, "open-jev--reasoning-control-v1-choice-test-v1": 0.5000000000000001, "open-jev--reasoning-control-v1-noul-test-v1": 0.5257352941176472, "open-jev--reasoning-control-v1-score-test-v1": 0.4566635975353456, "open-jev--silent-failure-control-v1-noul-test-v1": 0.7999999999999998, "open-jev--snake-v1-choice-test-v1": 0.09278350515463916, "open-jev--snake-v1-noul-test-v1": 0.0, "open-jev--sponsor-segment-control-v1-choice-test-v1": 0.9615384615384615, "open-jev--tic-tac-toe-v1-choice-test-v1": 0.0, "open-jev--vizdoom-basic-v1-noul-test-v1": 0.0, "open-jev--vizdoom-basic-v1-score-test-v1": 0.0, "open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.07925407925407923, "open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.5216645216645217, "open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.4237074401008827, "open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.8597475455820476, "openbookqa-choice-test-v1": 0.513888888888889, "patent-similarity-score-test-v1": 0.31252524547010985, "paws-noul-test-v1": 0.5800000000000001, "plane-noul-test-v1": 0.15999999999999992, "poem-sentiment-choice-test-v1": 0.0, "qasper-noul-test-v1": 0.5, "quartz-choice-test-v1": 0.5714285714285714, "robust-lr-choice-test-v1": 0.2833333333333332, "ruletaker-noul-test-v1": 0.19999999999999996, "s1mb-generalization-contextual-choice-choice-test-v1": 0.9356223175965664, "s1mb-generalization-contextual-noul-noul-test-v1": 0.8599999999999999, "s1mb-generalization-contextual-score-score-test-v1": 0.5807637701678208, "s1mb-generalization-diverse-choice-choice-test-v1": 0.8281938325991189, "s1mb-generalization-diverse-noul-noul-test-v1": 0.8199999999999998, "s1mb-generalization-diverse-score-score-test-v1": 0.542853674942144, "scicite-choice-test-v1": 0.5806451612903225, "scitail-noul-test-v1": 0.3599999999999999, "scone-choice-test-v1": 0.45999999999999996, "sdoh-nli-noul-test-v1": 0.7799999999999998, "sgd-choice-test-v1": 0.28813559322033894, "snli-choice-test-v1": 0.435483870967742, "spartqa-choice-test-v1": 0.0, "stepgame-choice-test-v1": 0.16666666666666666, "synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.24323236341159382, "synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.3514200661946152, "synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.338086317475911, "synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.39382915107171046, "synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.3121162821875584, "synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.15317608462017107, "synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.25432868872792525, "synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.5433401142954075, "synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.4092907693647627, "synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.31028836884860755, "synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.28151358723979114, "synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.4650246992966558, "synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.18347955342122924, "synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.10519955225802624, "synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.11690566856922147, "synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.43438990432557967, "synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.379596838141959, "synthetic-relevance--nanocoir-noul-test-v1": 0.4468861308059964, "synthetic-relevance--nanocoir-score-test-v1": 0.0, "temporal-nli-choice-test-v1": 0.20967741935483872, "tracie-noul-test-v1": 0.040000000000000036, "laya--typed-decisions-choice-test-v1": 0.25768202501015314, "laya--typed-decisions-noul-test-v1": 0.342119756005856, "laya--typed-decisions-score-test-v1": 0.260692037594918, "ud-ewt-choice-test-v1": 0.16043613707165108, "winobias-choice-test-v1": 0.1086956521739129, "winowhy-noul-test-v1": 0.19999999999999996, "wiqa-choice-test-v1": 0.19047619047619047 }, "noul": 0.42252965794032943, "choice": 0.4568250505770796, "score": 0.22878961534294814, "task_avg": 0.36938144128678574 }, "calibrated": { "adjusted": { "aegis2-noul-test-v1": 0.44539967075178355, "laya--ag-news-choice-test-v1": 0.8656716417910449, "aqua-rat-choice-test-v1": 0.042253521126760604, "arc-choice-test-v1": 0.7205882352941178, "arct-choice-test-v1": 0.17021276595744672, "argument-quality-choice-test-v1": 0.673469387755102, "argument-quality-noul-test-v1": 0.13869566972747505, "babi-nli-noul-test-v1": 0.6200000000000001, "banking77-choice-test-v1": 0.6105263157894737, "bbq-choice-test-v1": 0.7666666666666666, "boardgameqa-choice-test-v1": 0.09375, "canttalk-noul-test-v1": 0.6400000000000001, "civil-comments-noul-test-v1": 0.20946003197816698, "cladder-noul-test-v1": 0.020000000000000018, "clinc-choice-test-v1": 0.7724137931034483, "contract-nli-choice-test-v1": 0.4511930585683298, "corr2cause-choice-test-v1": 0.0, "creak-noul-test-v1": 0.48, "crows-pairs-choice-test-v1": 0.27083333333333337, "dbpedia-choice-test-v1": 0.9550561797752809, "defeasible-nli-choice-test-v1": 0.19565217391304343, "laya--enron-spam-noul-test-v1": 0.74, "esci-choice-test-v1": 0.17808219178082194, "ethics-choice-test-v1": 0.6666666666666665, "ethics-noul-test-v1": 0.3321428571428571, "ethos-noul-test-v1": 0.6200000000000001, "few-nerd-choice-test-v1": 0.5878136200716847, "fol-nli-choice-test-v1": 0.14754098360655732, "followir-core17-noul-test-v1": 0.3152680652680653, "followir-news21-noul-test-v1": 0.3799999999999999, "followir-robust04-noul-test-v1": 0.7176504797906369, "go-emotions-noul-test-v1": 0.4876902085539958, "gretel-pii-choice-test-v1": 0.6753246753246753, "gsm8k-choice-test-v1": 0.15714285714285714, "hans-noul-test-v1": 0.48, "hatecheck-noul-test-v1": 0.52, "hh-rlhf-choice-test-v1": 0.0, "hwu64-choice-test-v1": 0.7659574468085106, "impli-noul-test-v1": 0.54, "lexcomp-noul-test-v1": 0.3599999999999999, "logical-entailment-noul-test-v1": 0.1399999999999999, "lonli-choice-test-v1": 0.6229508196721312, "massive-choice-test-v1": 0.7477148080438757, "miqa-choice-test-v1": 0.7727272727272727, "mtop-choice-test-v1": 0.7144734182332727, "nlsat-noul-test-v1": 0.0, "open-jev--amount-extraction-control-v1-choice-test-v1": 0.7254901960784313, "open-jev--amount-extraction-control-v1-noul-test-v1": 0.15625, "open-jev--browser-control-v1-choice-test-v1": 0.6086956521739129, "open-jev--citation-control-v1-choice-test-v1": 0.7272727272727273, "open-jev--context-retention-control-v1-noul-test-v1": 0.0, "open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391, "open-jev--customer-control-v1-noul-test-v1": 0.8198529411764706, "open-jev--customer-control-v1-score-test-v1": 0.4187521241302211, "open-jev--drone-control-v1-choice-test-v1": 0.0, "open-jev--drone-control-v1-noul-test-v1": 0.9411764705882353, "open-jev--drone-control-v1-score-test-v1": 0.0, "open-jev--email-selection-control-v1-choice-test-v1": 0.21739130434782614, "open-jev--email-selection-control-v1-noul-test-v1": 0.6153846153846154, "open-jev--entity-alignment-control-v1-noul-test-v1": 0.3632478632478633, "open-jev--entity-alignment-control-v1-score-test-v1": 0.0, "open-jev--ir-control-v1-choice-test-v1": 0.7999999999999998, "open-jev--ir-control-v1-noul-test-v1": 0.7857142857142856, "open-jev--ir-control-v1-score-test-v1": 0.003762448219239989, "open-jev--mailroom-control-v1-choice-test-v1": 0.9166666666666667, "open-jev--mailroom-control-v1-noul-test-v1": 0.786111111111111, "open-jev--painting-geometry-v1-choice-test-v1": 0.5263157894736842, "open-jev--painting-geometry-v1-noul-test-v1": 0.4761904761904763, "open-jev--painting-geometry-v1-score-test-v1": 0.0, "open-jev--phone-extraction-control-v1-choice-test-v1": 0.5217391304347825, "open-jev--phone-extraction-control-v1-noul-test-v1": 0.30000000000000004, "open-jev--reasoning-control-v1-choice-test-v1": 0.5000000000000001, "open-jev--reasoning-control-v1-noul-test-v1": 0.5257352941176472, "open-jev--reasoning-control-v1-score-test-v1": 0.4850952557994459, "open-jev--silent-failure-control-v1-noul-test-v1": 0.7999999999999998, "open-jev--snake-v1-choice-test-v1": 0.09278350515463916, "open-jev--snake-v1-noul-test-v1": 0.0, "open-jev--sponsor-segment-control-v1-choice-test-v1": 0.9615384615384615, "open-jev--tic-tac-toe-v1-choice-test-v1": 0.0, "open-jev--vizdoom-basic-v1-noul-test-v1": 0.0, "open-jev--vizdoom-basic-v1-score-test-v1": 0.0, "open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.07925407925407923, "open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.5216645216645217, "open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.4237074401008827, "open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.8597475455820476, "openbookqa-choice-test-v1": 0.513888888888889, "patent-similarity-score-test-v1": 0.30384651191657186, "paws-noul-test-v1": 0.5800000000000001, "plane-noul-test-v1": 0.15999999999999992, "poem-sentiment-choice-test-v1": 0.0, "qasper-noul-test-v1": 0.5, "quartz-choice-test-v1": 0.5714285714285714, "robust-lr-choice-test-v1": 0.2833333333333332, "ruletaker-noul-test-v1": 0.19999999999999996, "s1mb-generalization-contextual-choice-choice-test-v1": 0.9356223175965664, "s1mb-generalization-contextual-noul-noul-test-v1": 0.8599999999999999, "s1mb-generalization-contextual-score-score-test-v1": 0.594086446068868, "s1mb-generalization-diverse-choice-choice-test-v1": 0.8281938325991189, "s1mb-generalization-diverse-noul-noul-test-v1": 0.8199999999999998, "s1mb-generalization-diverse-score-score-test-v1": 0.5760538063599603, "scicite-choice-test-v1": 0.5806451612903225, "scitail-noul-test-v1": 0.3599999999999999, "scone-choice-test-v1": 0.45999999999999996, "sdoh-nli-noul-test-v1": 0.7799999999999998, "sgd-choice-test-v1": 0.28813559322033894, "snli-choice-test-v1": 0.435483870967742, "spartqa-choice-test-v1": 0.0, "stepgame-choice-test-v1": 0.16666666666666666, "synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.24323236341159382, "synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.0, "synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.3514200661946152, "synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.34431685707848536, "synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.39382915107171046, "synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.3232729438947516, "synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.15317608462017107, "synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.2757512290222319, "synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.5433401142954075, "synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.42010774639672477, "synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.31028836884860755, "synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.29726958670945025, "synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.4650246992966558, "synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.2322138564292785, "synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.10519955225802624, "synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.13122383349369227, "synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.43438990432557967, "synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.3695734364304606, "synthetic-relevance--nanocoir-noul-test-v1": 0.4468861308059964, "synthetic-relevance--nanocoir-score-test-v1": 0.0, "temporal-nli-choice-test-v1": 0.20967741935483872, "tracie-noul-test-v1": 0.040000000000000036, "laya--typed-decisions-choice-test-v1": 0.25768202501015314, "laya--typed-decisions-noul-test-v1": 0.342119756005856, "laya--typed-decisions-score-test-v1": 0.25422877050308035, "ud-ewt-choice-test-v1": 0.16043613707165108, "winobias-choice-test-v1": 0.1086956521739129, "winowhy-noul-test-v1": 0.19999999999999996, "wiqa-choice-test-v1": 0.19047619047619047 }, "noul": 0.42252965794032943, "choice": 0.4568250505770796, "score": 0.23950261202154582, "task_avg": 0.3729524401796516 } } }, "leaderboard": [ { "model": "FINAL-Bench__Darwin-27B-ZTC-v9", "borda": 89.4549202487159, "noul": 74.81050701609263, "choice": 76.10256265688238, "score": 65.69946157747638, "task_avg": 72.2041770834838 }, { "model": "sqwish__kettei-fat-v1.0", "borda": 89.23695593403625, "noul": 73.47864112605596, "choice": 78.33753697215504, "score": 60.677673660012786, "task_avg": 70.83128391940792 }, { "model": "startlux-models__StartLux-Decision-v1.1-27B-Instant", "borda": 88.77399297107321, "noul": 74.28070126625073, "choice": 80.9689934716538, "score": 60.47420173900966, "task_avg": 71.90796549230473 }, { "model": "punkytiger__superion_s1", "borda": 88.68275209516082, "noul": 74.1544173754237, "choice": 82.76161505434226, "score": 66.1661284515905, "task_avg": 74.36072029378549 }, { "model": "vllm-sr__d3", "borda": 88.40227088402264, "noul": 72.76979659296646, "choice": 79.43823597745329, "score": 62.15350100760008, "task_avg": 71.45384452600659 }, { "model": "PelaAI__KnowLine-31B-Gen1", "borda": 87.92917004595832, "noul": 71.06337531128415, "choice": 76.01593574512474, "score": 63.27543646305255, "task_avg": 70.1182491731538 }, { "model": "FINAL-Bench__Darwin-27B-ZTC-v5", "borda": 87.44931062449307, "noul": 74.32352318504921, "choice": 72.25066441930817, "score": 65.25738278053589, "task_avg": 70.61052346163108 }, { "model": "perplexity-ai__pplx-decider-v1.2", "borda": 86.45241957285754, "noul": 71.63991167602491, "choice": 78.67069758233657, "score": 59.98685998614592, "task_avg": 70.0991564148358 }, { "model": "Maincode__matilda-jev-v1.5", "borda": 85.13787510137875, "noul": 70.92486162821892, "choice": 75.58328214021182, "score": 62.653655185778035, "task_avg": 69.72059965140292 }, { "model": "Superwheat__Gimbal-27B", "borda": 85.07873749662068, "noul": 72.64888110858253, "choice": 72.39510312615168, "score": 58.82642293307343, "task_avg": 67.95680238926921 }, { "model": "perplexity-ai__pplx-decider-v1.1-27b", "borda": 84.96384157880506, "noul": 71.38205356140031, "choice": 76.58026138262434, "score": 58.41767784792135, "task_avg": 68.79333093064866 }, { "model": "mukaddamzaid__amos-1-large", "borda": 84.78135982698028, "noul": 71.47255900056145, "choice": 77.60383254688709, "score": 49.98509963659832, "task_avg": 66.35383039468229 }, { "model": "torchcast-ai__torchcast-decision-27b", "borda": 84.41639632333064, "noul": 70.0633938779726, "choice": 73.80921735043513, "score": 57.43617546121547, "task_avg": 67.10292889654106 }, { "model": "PelaAI__KnowLine-35B-A3B-Gen1", "borda": 83.37557447958906, "noul": 67.81403265812658, "choice": 74.7408710871611, "score": 53.3391848116189, "task_avg": 65.29802951896886 }, { "model": "PelaAI__KnowLine-26B-A4B-Gen2", "borda": 83.28433360367666, "noul": 67.5690519789062, "choice": 72.81852030694385, "score": 52.064070423706234, "task_avg": 64.15054756985211 }, { "model": "shgao__rsi-jev-v6.1-vl-27b", "borda": 82.72168153555018, "noul": 67.95377166171617, "choice": 71.49713578075915, "score": 61.83374525924009, "task_avg": 67.09488423390513 }, { "model": "FINAL-Bench__Darwin-27B-ZTC-v2", "borda": 82.40909705325764, "noul": 67.65843776727887, "choice": 71.5072093161536, "score": 60.2135925895139, "task_avg": 66.45974655764878 }, { "model": "imguangyu__metaencoder_think", "borda": 80.96276020546095, "noul": 68.40085704143098, "choice": 74.68865311969675, "score": 62.157196191909556, "task_avg": 68.41556878434577 }, { "model": "vllm-sr__d3-flash", "borda": 80.75493376588267, "noul": 66.6111302967872, "choice": 74.73312296664545, "score": 46.47167335902383, "task_avg": 62.605308874152165 }, { "model": "PelaAI__KnowLine-4B-Gen5", "borda": 80.61300351446333, "noul": 65.65138406936738, "choice": 76.54750376209795, "score": 58.83559873081363, "task_avg": 67.01149552075964 }, { "model": "frontier-infra__jebadiah-27b", "borda": 80.55893484725604, "noul": 66.06741566951077, "choice": 67.7786419515256, "score": 53.94896592945718, "task_avg": 62.598341183497844 }, { "model": "fastino__glide", "borda": 80.21931603135981, "noul": 68.21691573894877, "choice": 72.21867107156177, "score": 51.88306305451613, "task_avg": 64.10621662167556 }, { "model": "PelaAI__KnowLine-9B-Gen1", "borda": 79.64314679643144, "noul": 64.39776873096814, "choice": 70.81963024662268, "score": 49.367916639323994, "task_avg": 61.528438538971606 }, { "model": "vllm-sr__Decision-2.0-Vega-27B", "borda": 79.23087320897544, "noul": 66.89352629736425, "choice": 70.21338348833062, "score": 42.94723908397514, "task_avg": 60.018049623223334 }, { "model": "sqwish__kettei-chub-v1.0", "borda": 79.06866720735333, "noul": 67.94710871859854, "choice": 70.70417091046505, "score": 45.63470436445472, "task_avg": 61.428661331172776 }, { "model": "openjev__openjev_27b_bf16", "borda": 78.81690997566912, "noul": 65.21616191434015, "choice": 67.74459368182643, "score": 54.82763584346644, "task_avg": 62.59613047987768 }, { "model": "vllm-sr__d3-mini", "borda": 78.71722087050551, "noul": 65.03865882654557, "choice": 71.19375863233792, "score": 46.37568943914048, "task_avg": 60.86936896600798 }, { "model": "perplexity-ai__pplx-decider-flash-v1.2", "borda": 78.65301432819679, "noul": 63.8734478128067, "choice": 73.27406036727218, "score": 44.65777650755283, "task_avg": 60.60176156254391 }, { "model": "jaredpalmer__kev-27b", "borda": 78.59049743173831, "noul": 66.65087911918437, "choice": 70.70791577670633, "score": 43.18481114363604, "task_avg": 60.181202013175586 }, { "model": "autotrust__JEV-27B", "borda": 78.21877534468776, "noul": 67.6453099367861, "choice": 67.72948464303629, "score": 54.976843994708915, "task_avg": 63.45054619151044 }, { "model": "denis-pplx__AutoJev-27B", "borda": 78.12753446877532, "noul": 64.96068056423817, "choice": 68.10599665053212, "score": 49.33934973953349, "task_avg": 60.80200898476793 }, { "model": "logic65__Whittle-Reflex-25B-A3B", "borda": 77.87408759124088, "noul": 65.35384776913521, "choice": 70.67223963282753, "score": 63.10444249477316, "task_avg": 66.37684329891196 }, { "model": "typesafe__jev_1_14_preview", "borda": 77.58177885915116, "noul": 65.0558566202727, "choice": 69.78676525630864, "score": 46.461284134075306, "task_avg": 60.43463533688554 }, { "model": "lihe07__span-02", "borda": 77.31650446066502, "noul": 63.602764397014546, "choice": 69.87903857921958, "score": 51.221110149015615, "task_avg": 61.56763770841658 }, { "model": "PelaAI__KnowLine-26B-A4B-Gen1", "borda": 77.14753987564207, "noul": 61.409353277703794, "choice": 69.64829608572035, "score": 43.05133673689556, "task_avg": 58.036328700106566 }, { "model": "theunnecessarythings__JADE", "borda": 76.11347661530145, "noul": 61.70080095759924, "choice": 66.57448959822455, "score": 55.43627214509025, "task_avg": 61.23718756697135 }, { "model": "OmniJev__OneJev1.6-27B", "borda": 76.06447688564481, "noul": 63.54010027741565, "choice": 69.88914285489403, "score": 46.90048800520919, "task_avg": 60.10991037917296 }, { "model": "typesafe__jev_1_13", "borda": 76.01040821843742, "noul": 64.63433927735257, "choice": 67.21804084276843, "score": 46.918451356443185, "task_avg": 59.59027715885473 }, { "model": "caiovicentino1__Eikos-27B", "borda": 75.89044336307103, "noul": 64.1370897159886, "choice": 67.61278489453032, "score": 47.833150601627935, "task_avg": 59.86100840404895 }, { "model": "e12ex2__jev-vision-27b", "borda": 75.07434441741007, "noul": 64.04436182267986, "choice": 65.93713695074054, "score": 48.500124275408, "task_avg": 59.49387434960946 }, { "model": "OmniJev__OneJev1.5-27B", "borda": 74.668829413355, "noul": 61.09501894474635, "choice": 69.87649691951748, "score": 47.938519484675226, "task_avg": 59.636678449646354 }, { "model": "5ak3t__scm_max_14b_v1", "borda": 74.55055420383889, "noul": 60.51181830885981, "choice": 66.65372054368405, "score": 39.22091797154031, "task_avg": 55.46215227469472 }, { "model": "cribl__decision-1.0-27B", "borda": 73.34583671262506, "noul": 58.23245852051888, "choice": 67.317861895564, "score": 49.5166582149999, "task_avg": 58.35565954369426 }, { "model": "PixilabAI__Blink-v0.3-26B-A4B-NVFP4", "borda": 73.2191132738578, "noul": 61.68945323627374, "choice": 66.14093862930842, "score": 55.31595651133141, "task_avg": 61.04878279230452 }, { "model": "juspay__Xor-26B-A4B", "borda": 73.01297648012977, "noul": 62.011868472600995, "choice": 67.03600249426962, "score": 31.88512034587986, "task_avg": 53.6443304375835 }, { "model": "Cloudflare__clef", "borda": 72.98763179237638, "noul": 61.62730332999063, "choice": 67.20169633565135, "score": 39.082881095062675, "task_avg": 55.97062692023489 }, { "model": "PelaAI__KnowLine-4B-Gen3", "borda": 72.67504731008384, "noul": 59.97018440461604, "choice": 65.48596192877402, "score": 46.44983643291625, "task_avg": 57.30199425543544 }, { "model": "PelaAI__KnowLine-4B-Gen4", "borda": 72.15970532576372, "noul": 59.7814276733928, "choice": 64.98264621333891, "score": 44.39828763620016, "task_avg": 56.38745384097729 }, { "model": "autotrust__GEV-26B-Decide", "borda": 71.38753717220871, "noul": 61.897586797625806, "choice": 66.80357393074135, "score": 36.232251710077016, "task_avg": 54.977804146148046 }, { "model": "michaelfeil__rune-26b-a4b", "borda": 70.94147066774806, "noul": 58.56463370433087, "choice": 64.36358265014647, "score": 51.57246351871485, "task_avg": 58.166893291064056 }, { "model": "OURS:rl60_routed30", "borda": 70.69309272776422, "noul": 58.27471502074819, "choice": 67.63083260170816, "score": 39.777315533393434, "task_avg": 55.227621051949924 }, { "model": "PelaAI__KnowLine-4B-Gen2", "borda": 70.31968099486345, "noul": 58.72155491154057, "choice": 64.0505785467449, "score": 42.99430713187057, "task_avg": 55.25548019671868 }, { "model": "andyzhang232__ajev-gemma4-12b-lora5", "borda": 70.02906190862397, "noul": 59.947985038400475, "choice": 61.77736117267184, "score": 42.902281691801605, "task_avg": 54.87587596762463 }, { "model": "EldanRing__Winnow-12B", "borda": 69.02034333603677, "noul": 61.38007245783731, "choice": 60.69557820772463, "score": 41.61464332348616, "task_avg": 54.5634313296827 }, { "model": "vllm-sr__Decision-2.0-Lux-9B", "borda": 67.5638686131387, "noul": 55.22550956774106, "choice": 60.745127626074826, "score": 39.14262240520837, "task_avg": 51.70441986634141 }, { "model": "juspay__jev-one", "borda": 66.69032170856988, "noul": 56.42824286907736, "choice": 60.78598989989204, "score": 39.703599336592085, "task_avg": 52.30594403518717 }, { "model": "hotchpotch__saihai-v1-8b", "borda": 66.44701270613676, "noul": 59.96326955105372, "choice": 59.50955138563523, "score": 32.29351303767978, "task_avg": 50.58877799145625 }, { "model": "kirp__jpt-9b", "borda": 66.27128953771289, "noul": 55.27194977131644, "choice": 61.86869369858429, "score": 38.48880869670963, "task_avg": 51.876484055536785 }, { "model": "facebook__meta-encoder-cosine-t0.0184671662", "borda": 66.1766693701, "noul": 58.083454678598926, "choice": 61.53247777642923, "score": 31.041417232334425, "task_avg": 50.21911656245419 }, { "model": "shgao__rsi-jev-v6.1-vl-4b", "borda": 66.1699107866991, "noul": 58.71382196252589, "choice": 60.155733062517605, "score": 34.6320139533932, "task_avg": 51.16718965947889 }, { "model": "bespokelabs__Bespoke-Nimble-9B-v3", "borda": 65.86915382535821, "noul": 54.77071642710267, "choice": 62.238226340415316, "score": 39.52578098159997, "task_avg": 52.17824124970599 }, { "model": "OmniJev__OneJev1.5-9B", "borda": 64.77088402270881, "noul": 51.549561609277674, "choice": 60.397532590452826, "score": 32.61798123492535, "task_avg": 48.188358478218625 }, { "model": "Cloudflare__clef-flash", "borda": 63.80947553392807, "noul": 51.81658406094412, "choice": 63.05238235307888, "score": 29.317245033831874, "task_avg": 48.062070482618296 }, { "model": "hotchpotch__bekko-system-one-v0-400m", "borda": 63.07447958907812, "noul": 51.23656603425154, "choice": 61.31612420623802, "score": 39.248477224230605, "task_avg": 50.60038915490672 }, { "model": "frontier-infra__jebadiah-9b-v2", "borda": 62.934238983509054, "noul": 53.302174585046544, "choice": 58.22725190376157, "score": 34.47869550166637, "task_avg": 48.66937399682483 }, { "model": "Mapika__decider-35b-a3b", "borda": 62.68417139767504, "noul": 54.76743959294037, "choice": 59.920146312776545, "score": 25.355920318146346, "task_avg": 46.681168741287756 }, { "model": "OmniJev__OneJev1.6-9B", "borda": 62.31582860232495, "noul": 49.01025150665736, "choice": 61.20405372330777, "score": 29.028362215106267, "task_avg": 46.41422248169047 }, { "model": "ZefanCai__Open-Jev-27B-v1.1", "borda": 62.29724249797241, "noul": 51.47692283969588, "choice": 66.91252355646577, "score": 52.25918085490528, "task_avg": 56.88287575035565 }, { "model": "theaviv__Lev1-3.7B", "borda": 62.06407137064071, "noul": 57.96208481407391, "choice": 60.406478185370084, "score": 32.141977592905654, "task_avg": 50.17018019744989 }, { "model": "kirp__jpt-4b", "borda": 61.964382265477184, "noul": 55.383345312989064, "choice": 56.752909682248124, "score": 36.06967904698538, "task_avg": 49.40197801407418 }, { "model": "vllm-sr__Decision-2.0-Nox-4B", "borda": 61.94917545282511, "noul": 51.699137853991296, "choice": 57.16912445060331, "score": 37.10346511290773, "task_avg": 48.65724247250078 }, { "model": "vllm-sr__d3-nano", "borda": 61.78865909705327, "noul": 51.40453253890441, "choice": 60.33571490530164, "score": 30.213438941645656, "task_avg": 47.31789546195057 }, { "model": "frontier-infra__jebadiah-9b-v0", "borda": 61.47438496891052, "noul": 52.107687627842125, "choice": 56.65043516037408, "score": 38.22000861676978, "task_avg": 48.99271046832867 }, { "model": "bespokelabs__Bespoke-Nimble-9B", "borda": 61.16349013246825, "noul": 52.59016873865345, "choice": 56.98874631196198, "score": 31.783933399654117, "task_avg": 47.12094948342318 }, { "model": "5ak3t__scm_max_14b_v0", "borda": 60.916801838334685, "noul": 50.09046799789556, "choice": 55.36828314970512, "score": 32.3116435197021, "task_avg": 45.92346488910093 }, { "model": "OURS:rl60", "borda": 60.50790754257907, "noul": 50.70371577975563, "choice": 57.19274044054583, "score": 35.767117161735676, "task_avg": 47.88785779401238 }, { "model": "openai__gpt-6-luna-decisions", "borda": 60.448769937821034, "noul": 54.54085821490578, "choice": 56.23257426488686, "score": 36.84663806748401, "task_avg": 49.206690182425554 }, { "model": "mohit67890__imajev-9b", "borda": 60.403149499864845, "noul": 54.001619796730594, "choice": 58.287980587192536, "score": 23.14132659704442, "task_avg": 45.14364232698918 }, { "model": "empiriolabsai__aplomb-1", "borda": 60.30346039470126, "noul": 52.43316942953806, "choice": 54.79683599028732, "score": 35.009688942999766, "task_avg": 47.41323145427504 }, { "model": "shgao__rsi-jev-v5.0-vl-3b", "borda": 60.07366855907002, "noul": 56.703209225209065, "choice": 55.45133278638838, "score": 29.60071776434164, "task_avg": 47.25175325864635 }, { "model": "akhilaaa3__Jev-Omni", "borda": 60.04156528791562, "noul": 55.66517298237154, "choice": 54.75495804543774, "score": 33.380992759919344, "task_avg": 47.93370792924287 }, { "model": "mohit67890__imajev-4b", "borda": 59.9249797242498, "noul": 53.48572346871568, "choice": 56.70130078423596, "score": 28.40857443345301, "task_avg": 46.19853289546822 }, { "model": "sthanika-ai__Sieve-9B", "borda": 59.6140848878075, "noul": 51.240803885533225, "choice": 57.24807805511779, "score": 28.67039450941818, "task_avg": 45.719758816689726 }, { "model": "eljiwo__jiwo-4b", "borda": 59.49074074074073, "noul": 52.65877502202466, "choice": 55.02139973370082, "score": 31.00492474270615, "task_avg": 46.22836649947721 }, { "model": "michaljach__jet", "borda": 59.28798323871317, "noul": 51.024653480610084, "choice": 53.74774297160457, "score": 33.01172599080244, "task_avg": 45.928040814339035 }, { "model": "everettjf__ezjev-4b-s2", "borda": 59.068329278183285, "noul": 50.89605291103704, "choice": 57.34730010900303, "score": 34.75755858279741, "task_avg": 47.66697053427916 }, { "model": "alibiserikbay__JevK5-9B", "borda": 58.72195187888618, "noul": 52.8766435353212, "choice": 56.67250455930102, "score": 23.87040931557622, "task_avg": 44.47318580339948 }, { "model": "ZefanCai__Open-Jev-9B", "borda": 58.61381454447151, "noul": 55.75509897557962, "choice": 55.51380128740718, "score": 45.03514620643869, "task_avg": 52.10134882314183 }, { "model": "jsaurabh__qwen3.5-9b-jev-data-mix-v2", "borda": 58.0308867261422, "noul": 51.19384350959355, "choice": 51.08361612498409, "score": 33.53590738843635, "task_avg": 45.27112234100466 }, { "model": "apus-ailab__APUS-OpenJev-v1-9B", "borda": 57.758853744255205, "noul": 49.13784280054897, "choice": 53.91768197623167, "score": 31.09373253631511, "task_avg": 44.71641910436525 }, { "model": "PelaAI__KnowLine-2B-Gen1", "borda": 57.04920248715871, "noul": 48.42044984584481, "choice": 57.3876989661614, "score": 28.73278522706909, "task_avg": 44.8469780130251 }, { "model": "togethercomputer__Tev1-4B-experimental", "borda": 56.95796161124626, "noul": 50.728319922771725, "choice": 53.35818184686657, "score": 37.111928168339126, "task_avg": 47.06614331265914 }, { "model": "Mapika__decider-4b", "borda": 56.854893214382294, "noul": 52.40292363906677, "choice": 53.992784562008985, "score": 22.117985237066858, "task_avg": 42.8378978127142 }, { "model": "frontier-infra__jebadiah-4b-v2", "borda": 56.76703163017033, "noul": 48.858914095700776, "choice": 54.819709035764284, "score": 32.87631710043918, "task_avg": 45.518313410634754 }, { "model": "apus-ailab__APUS-OpenJev-v1-4B", "borda": 56.481481481481474, "noul": 50.213300414471185, "choice": 51.4927844560767, "score": 31.6552861011774, "task_avg": 44.45379032390843 }, { "model": "OmniJev__OneJev1.6-4B", "borda": 56.371654501216575, "noul": 46.99999602368463, "choice": 57.112714382717165, "score": 26.095264486295598, "task_avg": 43.4026582975658 }, { "model": "CountingSheep__vev-9b", "borda": 56.246620708299545, "noul": 49.17221842703725, "choice": 56.61914987767809, "score": 23.004241643862912, "task_avg": 42.931869982859425 }, { "model": "EldanRing__Winnow-E4B", "borda": 55.73972695323064, "noul": 51.540622380366926, "choice": 52.334647835879785, "score": 32.22216291323428, "task_avg": 45.365811043160335 }, { "model": "StandardThinking__StandardOne-8B", "borda": 55.64848607731817, "noul": 52.9291533583201, "choice": 49.06930731501095, "score": 26.35668319514521, "task_avg": 42.785047956158756 }, { "model": "jaredpalmer__kev-9b", "borda": 55.62821032711544, "noul": 50.20671642811111, "choice": 56.36143243775897, "score": 20.63580286164106, "task_avg": 42.40131724250371 }, { "model": "evalengine__decision-4b", "borda": 55.239591781562574, "noul": 50.164139724054266, "choice": 53.17461756459602, "score": 33.65457848947355, "task_avg": 45.66444525937462 }, { "model": "abhishek085__spark-s1-4b-v6", "borda": 55.1449716139497, "noul": 51.80307006362222, "choice": 49.76591502898487, "score": 33.83453084970998, "task_avg": 45.134505314105695 }, { "model": "OURS:v1_joint", "borda": 54.79183563125168, "noul": 50.07962257490453, "choice": 52.30924425272342, "score": 27.975023045764445, "task_avg": 43.45462995779747 }, { "model": "TokenRhythm__NeoHorse-Jev-4B", "borda": 53.801703163017045, "noul": 48.33247276234772, "choice": 52.761591848959476, "score": 29.700346169829544, "task_avg": 43.59813692704558 }, { "model": "jaredpalmer__kev-4b", "borda": 53.64287645309544, "noul": 48.4774594752686, "choice": 52.034952823700706, "score": 26.470899581663804, "task_avg": 42.3277706268777 }, { "model": "bespokelabs__Bespoke-Nimble-9B-v2", "borda": 53.28129224114622, "noul": 46.02391167595726, "choice": 55.71719728128821, "score": 24.460288843686584, "task_avg": 42.06713260031068 }, { "model": "uneeverse__unee-2b", "borda": 53.13429305217627, "noul": 45.59951252551379, "choice": 52.64336596463589, "score": 35.00483267241027, "task_avg": 44.41590372085331 }, { "model": "caiovicentino1__Eikos-4B", "borda": 52.80988104893216, "noul": 49.03191091243997, "choice": 52.20046871910717, "score": 22.24212386108504, "task_avg": 41.158167830877396 }, { "model": "flymy-ai__decision-4b-v1.1", "borda": 52.49391727493917, "noul": 47.715308394774105, "choice": 48.47537367583929, "score": 28.68205617290122, "task_avg": 41.62424608117155 }, { "model": "dhtocks__malkuth-4b", "borda": 52.291159772911605, "noul": 48.13267469024474, "choice": 53.78319033513599, "score": 21.089741327302296, "task_avg": 41.001868784227675 }, { "model": "alibiserikbay__JevK5", "borda": 52.15598810489322, "noul": 48.92717406282948, "choice": 52.84174756452853, "score": 21.648399133484318, "task_avg": 41.139106920280774 }, { "model": "interfaze-ai__lev", "borda": 52.123884833738856, "noul": 45.00380964688521, "choice": 52.978836772077834, "score": 23.021133906488345, "task_avg": 40.33459344181713 }, { "model": "HopitAI__hopper", "borda": 51.91943768586106, "noul": 49.92860136088426, "choice": 49.00742580162692, "score": 22.50867013185354, "task_avg": 40.481565764788236 }, { "model": "CountingSheep__vev-4b", "borda": 51.4683022438497, "noul": 47.938653157953674, "choice": 51.19792526452689, "score": 21.055236490664544, "task_avg": 40.0639383043817 }, { "model": "hotchpotch__bekko-system-one-v0-68m", "borda": 51.44802649364691, "noul": 42.913061338083594, "choice": 51.6181937632021, "score": 26.845989503564372, "task_avg": 40.45908153495002 }, { "model": "flymy-ai__decision-4b-v1.2", "borda": 50.02027575020277, "noul": 47.32481945457459, "choice": 48.07060178870557, "score": 25.472043244269898, "task_avg": 40.28915482918335 }, { "model": "vllm-sr__d3-lite", "borda": 49.619829683698306, "noul": 43.48613150148678, "choice": 51.892808643346754, "score": 20.68741614064444, "task_avg": 38.68878542849266 }, { "model": "oraculumai__Manchego", "borda": 48.25966477426332, "noul": 47.04604178545591, "choice": 45.14757039190996, "score": 19.804282017145038, "task_avg": 37.33263139817031 }, { "model": "hotchpotch__saihai-v1-310m", "borda": 47.52973776696408, "noul": 40.92421104645248, "choice": 47.198442747238445, "score": 33.65849860409062, "task_avg": 40.59371746592718 }, { "model": "AlexWortega__openjev--qwen3.5-4b-nli-v5", "borda": 47.33711814003785, "noul": 42.771292706774986, "choice": 47.49208578199777, "score": 19.105679109219206, "task_avg": 36.456352532663985 }, { "model": "crh225__plumb-4b", "borda": 47.1512570965126, "noul": 44.76249223405814, "choice": 45.370383998009764, "score": 21.489386935461948, "task_avg": 37.207421055843284 }, { "model": "wayfind__metask-jev-4b-policy-mix", "borda": 46.61901865369019, "noul": 44.06001452621817, "choice": 46.15624352503484, "score": 20.36866645662884, "task_avg": 36.86164150262729 }, { "model": "AmirBraham__jevstral-8b", "borda": 46.41288185996213, "noul": 44.108287297215774, "choice": 48.90426519874536, "score": 12.887721999075769, "task_avg": 35.30009149834563 }, { "model": "kshetrajna12__reflex-qwen3.5-4b-lora", "borda": 45.84178156258446, "noul": 46.897123335085354, "choice": 44.688947310079996, "score": 15.888206351428474, "task_avg": 35.82475899886461 }, { "model": "jaredpalmer__kev-8b", "borda": 45.75391997837253, "noul": 41.040239693696904, "choice": 47.53947005827517, "score": 19.445423228052107, "task_avg": 36.008377660008065 }, { "model": "kpiya__kas-4b", "borda": 45.4497837253312, "noul": 42.308812674285434, "choice": 51.23386959437334, "score": 14.33021359577897, "task_avg": 35.95763195481258 }, { "model": "OURS:v2_2b_ro", "borda": 44.95302784536361, "noul": 42.252965794032946, "choice": 45.682505057707964, "score": 23.950261202154582, "task_avg": 37.29524401796516 }, { "model": "uneeverse__unee-0.8b", "borda": 43.87672343876726, "noul": 42.43363587439376, "choice": 41.416221928478066, "score": 22.508777339193227, "task_avg": 35.452878380688354 }, { "model": "chaoliangUNSW__Jev-Style-2B-Decision-v3", "borda": 43.42389835090567, "noul": 39.99393767141549, "choice": 45.94280668155854, "score": 18.369204941297397, "task_avg": 34.768649764757136 }, { "model": "vllm-sr__Decision-2.0-Sol-2B", "borda": 43.40531224655312, "noul": 37.45424316002706, "choice": 44.19198049340873, "score": 18.786574596041465, "task_avg": 33.477599416492424 }, { "model": "pngwn__system-one-qwen3.5-4b-scorer", "borda": 43.00993511759934, "noul": 40.278468045993684, "choice": 43.931154644733134, "score": 12.705857703586062, "task_avg": 32.305160131437624 }, { "model": "PelaAI__KnowLine-0.8B-Gen1", "borda": 42.572316842389796, "noul": 37.08432082593905, "choice": 47.15612284001329, "score": 18.259239046267105, "task_avg": 34.16656090407315 }, { "model": "GestaltLabs__Jeff-1", "borda": 42.09921600432553, "noul": 38.370081367789524, "choice": 38.63294657292472, "score": 32.916423644618426, "task_avg": 36.63981719511089 }, { "model": "5ak3t__scm_mid_4b_v1", "borda": 41.68525277101919, "noul": 45.92198337424015, "choice": 38.21709098037366, "score": 6.303910416270853, "task_avg": 30.147661590294888 }, { "model": "UserMoonlight__intelif-qwen3-4b", "borda": 41.621046228710455, "noul": 35.931771284623764, "choice": 44.584519858722324, "score": 11.26538983929321, "task_avg": 30.59389366087976 }, { "model": "pngwn__system-one-qwen3.5-4b-scorer-v2b", "borda": 40.71201676128682, "noul": 40.73096581608453, "choice": 47.49872109068542, "score": 11.255482531382844, "task_avg": 33.16172314605093 }, { "model": "mstrasser__Jeff-Gemma4-E2B", "borda": 40.28960529872938, "noul": 37.490263602369964, "choice": 41.97100505496683, "score": 14.528356623257475, "task_avg": 31.329875093531424 }, { "model": "mstrasser__Jeff-Qwen3.5-2B", "borda": 40.10543390105433, "noul": 37.88530508490729, "choice": 43.103576532513785, "score": 15.156137149433471, "task_avg": 32.048339588951514 }, { "model": "OURS:base", "borda": 40.046296296296305, "noul": 33.76706817616705, "choice": 45.70255576401406, "score": 18.882231543636387, "task_avg": 32.78395182793917 }, { "model": "flymy-ai__decision-2b-preview", "borda": 39.99560692078941, "noul": 37.88320498017567, "choice": 37.75292647800017, "score": 17.14077374439567, "task_avg": 30.92563506752384 }, { "model": "davidburhans__gevva-e4b", "borda": 39.64585022979185, "noul": 40.546151435239565, "choice": 42.80001198616829, "score": 4.22575655315711, "task_avg": 29.190639991521657 }, { "model": "flock-io__this-that-model-1.2", "borda": 39.24540416328738, "noul": 35.1017754925684, "choice": 43.488813331032325, "score": 15.372714102370214, "task_avg": 31.321100975323645 }, { "model": "ZefanCai__Open-Jev-2B", "borda": 39.123749662070814, "noul": 38.83305311842163, "choice": 39.82442308077451, "score": 25.268369720547007, "task_avg": 34.64194863991438 }, { "model": "Mapika__decider-2b", "borda": 39.12206001622061, "noul": 38.57729999894551, "choice": 39.31728653105371, "score": 10.388387284592177, "task_avg": 29.42765793819714 }, { "model": "mohit67890__imajev-2b", "borda": 38.97675047310085, "noul": 37.70378357523272, "choice": 43.031172624025935, "score": 11.685794338472851, "task_avg": 30.806916845910504 }, { "model": "vllm-sr__d3-edge", "borda": 38.06772100567721, "noul": 32.99872964035195, "choice": 41.35124914551756, "score": 13.657641531976411, "task_avg": 29.335873439281972 }, { "model": "hotchpotch__bekko-system-one-v0-17m", "borda": 37.78048121113814, "noul": 31.43315941534458, "choice": 35.56540565712225, "score": 15.700463916883209, "task_avg": 27.566342996450015 }, { "model": "dhtocks__malkuth-2b", "borda": 37.412138415788036, "noul": 35.926391917345285, "choice": 39.012742590961224, "score": 12.353633749590351, "task_avg": 29.09758941929896 }, { "model": "OmniJev__OneJev1.6-0.8B", "borda": 37.38848337388484, "noul": 36.62715426323174, "choice": 39.09571539244136, "score": 14.372384217745191, "task_avg": 30.03175129113943 }, { "model": "davidburhans__gevva-e2b", "borda": 37.38003514463368, "noul": 39.150340975100036, "choice": 39.074866297421956, "score": 6.018645382635025, "task_avg": 28.081284218385676 }, { "model": "AnkitAI__TinyJev-4B", "borda": 37.33779399837793, "noul": 32.24141943416321, "choice": 42.672562541753514, "score": 12.398819911183608, "task_avg": 29.104267295700115 }, { "model": "kirp__jpt-0.8b", "borda": 36.883279264666136, "noul": 38.354356448823864, "choice": 36.85227432583024, "score": 11.870674563388144, "task_avg": 29.025768446014084 }, { "model": "eljiwo__jiwo-0.8b", "borda": 36.06211138145445, "noul": 36.35547403770529, "choice": 33.71114762929817, "score": 15.295423952393103, "task_avg": 28.45401520646552 }, { "model": "OmniJev__OneJev1.5-0.8B", "borda": 34.97566909975668, "noul": 32.303165490281074, "choice": 37.50987898646421, "score": 14.579994355364848, "task_avg": 28.13101294403671 }, { "model": "vllm-sr__Decision-2.0-Eos-0.8B", "borda": 34.31670721816707, "noul": 28.84799678052876, "choice": 34.95839771196565, "score": 15.532451501232206, "task_avg": 26.446281997908873 }, { "model": "carrtesy__EXAONE-4.0-1.2B-JEV", "borda": 33.84698567180318, "noul": 32.12673137770427, "choice": 39.26135941492968, "score": 8.16470117641795, "task_avg": 26.5175973230173 }, { "model": "mstrasser__Jeff-Qwen3.5-0.8B", "borda": 33.05623141389564, "noul": 31.224289193970566, "choice": 34.695601494309024, "score": 11.998621454259574, "task_avg": 25.972837380846386 }, { "model": "sthanika-ai__sieve-2b", "borda": 32.990335225736686, "noul": 33.799584652254325, "choice": 35.150391005039495, "score": 7.322320615018016, "task_avg": 25.42409875743728 }, { "model": "Hanno-Labs__bosun-v3.1-1.7b", "borda": 32.69295755609627, "noul": 28.04997349025108, "choice": 28.081958912239397, "score": 20.427989896267544, "task_avg": 25.51997409958601 }, { "model": "Mapika__decider-2b-vision", "borda": 32.61354420113544, "noul": 34.10575498627405, "choice": 32.24739614073577, "score": 10.188694403829833, "task_avg": 25.51394851027989 }, { "model": "AlexWortega__openjev--qwen3.5-2b-nli-v5", "borda": 31.596377399297104, "noul": 29.723388227975022, "choice": 37.79538324399946, "score": 8.112348380903406, "task_avg": 25.21037328429263 }, { "model": "OmniJev__OneJev-0.8B", "borda": 31.211138145444703, "noul": 30.463820211555774, "choice": 30.748756859069452, "score": 7.925767920224533, "task_avg": 23.04611499694992 }, { "model": "chaoliangUNSW__Jev-Style-0.8B-Decision-v3", "borda": 31.042173560421734, "noul": 28.184107627974807, "choice": 28.836727605936392, "score": 9.672658176118954, "task_avg": 22.231164470010047 }, { "model": "Mapika__decider-0.8b", "borda": 30.986415247364157, "noul": 28.9673685086067, "choice": 32.357637367388755, "score": 6.392707984749325, "task_avg": 22.572571286914926 }, { "model": "vllm-sr__Decision-2.0-Kai-0.6B", "borda": 30.76676128683428, "noul": 28.39671715679961, "choice": 34.27585259456087, "score": 6.968857069956099, "task_avg": 23.213808940438863 }, { "model": "AndeyTait__JevForge-0.8B", "borda": 30.640037848067045, "noul": 29.860761769678785, "choice": 25.032095488629245, "score": 15.694452283576018, "task_avg": 23.52910318062802 }, { "model": "togethercomputer__Tev1-0.8B-experimental", "borda": 27.618951067856177, "noul": 25.97343515742046, "choice": 27.1457200719027, "score": 8.163037094833115, "task_avg": 20.427397441385423 }, { "model": "OURS:base_2b", "borda": 26.334820221681532, "noul": 22.871795602410288, "choice": 29.531777580453237, "score": 2.0098659488690807, "task_avg": 18.13781304391087 }, { "model": "Hanno-Labs__bosun-v3.1-0.6b", "borda": 26.1574074074074, "noul": 24.90439276593173, "choice": 20.491384948080473, "score": 12.559630477597267, "task_avg": 19.318469397203156 }, { "model": "LMDHQ-0420__vision-jev-9b", "borda": 25.98844282238442, "noul": 25.295203567189844, "choice": 25.983634193949495, "score": 0.6645502392581939, "task_avg": 17.31446266679918 }, { "model": "divyanshx11__JEVision", "borda": 25.951270613679373, "noul": 22.40803103996612, "choice": 26.880345865049794, "score": 6.197743716965625, "task_avg": 18.49537354066051 }, { "model": "jaredpalmer__kev-0.8b", "borda": 25.88368477967018, "noul": 23.611325424298922, "choice": 27.36222624924885, "score": 5.071763261606087, "task_avg": 18.68177164505129 }, { "model": "iapp__OpenThai-SystemOne", "borda": 25.415652879156532, "noul": 22.367327037534988, "choice": 26.22135868241336, "score": 7.3714975885457505, "task_avg": 18.653394436164696 }, { "model": "Lukitaduarte__dinah-0", "borda": 25.29737766964044, "noul": 16.820408366046614, "choice": 26.739988868819776, "score": 11.361591789920888, "task_avg": 18.307329674929093 }, { "model": "FrontiersMind__Lumma-fev-0.6b", "borda": 24.76344958096784, "noul": 17.60554805520938, "choice": 21.15225656054735, "score": 24.3078689655222, "task_avg": 21.021891193759643 }, { "model": "wfzyx__von", "borda": 24.0757637199243, "noul": 20.150537695397656, "choice": 23.985557398038075, "score": 4.4792196377932, "task_avg": 16.205104910409645 }, { "model": "Qwen__Qwen3-Reranker-4B", "borda": 23.89666125979994, "noul": 17.62881435769582, "choice": 28.913615050637947, "score": 1.620679097735405, "task_avg": 16.054369502023054 }, { "model": "mohamedlotfy50__sifr-0.8b-v3", "borda": 23.88145444714789, "noul": 23.666774320228065, "choice": 23.95722554543709, "score": 1.6177606557694186, "task_avg": 16.413920173811526 }, { "model": "convaiinnovations__laya-typed-decisions", "borda": 23.670248715869143, "noul": 20.062833690097438, "choice": 18.931880597379365, "score": 5.994198619698101, "task_avg": 14.996304302391636 }, { "model": "AlexWortega__openjev--qwen3.5-0.8b-nli-v2s-long", "borda": 23.095769126791026, "noul": 18.902225279875033, "choice": 23.79105791052257, "score": 5.359923474119997, "task_avg": 16.0177355548392 }, { "model": "moganai__lavoir", "borda": 22.62773722627737, "noul": 18.93986239283059, "choice": 18.203270080976015, "score": 2.9992074600505156, "task_avg": 13.380779977952376 }, { "model": "zeroentropy__zerank-2-reranker", "borda": 22.57704785077047, "noul": 13.326420068720996, "choice": 31.962061490160533, "score": 1.4433007397282875, "task_avg": 15.57726076620327 }, { "model": "convaiinnovations__laya", "borda": 22.13098134630981, "noul": 20.192323410725066, "choice": 16.305950464357625, "score": 3.5838472739440608, "task_avg": 13.360707049675586 }, { "model": "jaredpalmer__kev-0.6b", "borda": 22.056636928899703, "noul": 14.688412314113597, "choice": 24.025031451357542, "score": 3.5063424994417294, "task_avg": 14.07326208830429 }, { "model": "flymy-ai__decision-fast-preview", "borda": 21.718707758853743, "noul": 18.22846972115562, "choice": 23.740218206765924, "score": 2.0278130142512443, "task_avg": 14.665500314057597 }, { "model": "LibertAIDAI__deem-0.8-v1", "borda": 21.488915923222493, "noul": 18.10126399278811, "choice": 13.611952791316394, "score": 2.1374360232394505, "task_avg": 11.283550935781319 }, { "model": "PIXELZX__XERON-0.1", "borda": 20.6728169775615, "noul": 15.031335732742432, "choice": 15.554782929993724, "score": 4.132084549379842, "task_avg": 11.572734404038666 }, { "model": "monotykamary__LFM2.5-2.6B-RLCD", "borda": 20.517369559340366, "noul": 19.154322729808044, "choice": 13.759507629852768, "score": 2.626183028303241, "task_avg": 11.84667112932135 }, { "model": "AnkitAI__tinyjev-0.6b", "borda": 19.84995944849959, "noul": 10.935794989960982, "choice": 23.101353232919642, "score": 3.250148445911695, "task_avg": 12.429098889597439 }, { "model": "mghafiri__qwen3.5-0.8B-decision-model", "borda": 18.98317112733171, "noul": 14.329981250198824, "choice": 19.49529077682183, "score": 3.699777909110459, "task_avg": 12.508349978710367 }, { "model": "mstrasser__Jeff-Qwen3.5-0.8B-Chess", "borda": 18.844620167612867, "noul": 14.50634308737809, "choice": 19.390990393552094, "score": 2.429120508652862, "task_avg": 12.108817996527682 }, { "model": "LMDHQ-0420__vision-jev-0.8b", "borda": 18.663828061638288, "noul": 20.881038870188878, "choice": 9.818740425946064, "score": 0.1983723251182467, "task_avg": 10.299383873751063 }, { "model": "convaiinnovations__laya-multilingual", "borda": 18.525277101919436, "noul": 14.010551486645076, "choice": 13.030684525327096, "score": 0.7943755407276067, "task_avg": 9.278537184233258 }, { "model": "isHeSatoshi__smalljev-semantic-v9", "borda": 18.060624493106246, "noul": 19.52428131944893, "choice": 1.045241269905861, "score": 2.9785716827411277, "task_avg": 7.849364757365307 }, { "model": "com-kotobalabs__open-jev-deberta-v3-large", "borda": 16.974182211408486, "noul": 6.990852278746, "choice": 21.675329226292998, "score": 1.4836375647889881, "task_avg": 10.049939689942661 }, { "model": "jaredpalmer__kev-0.5b", "borda": 16.644701270613677, "noul": 9.708535887222626, "choice": 18.649924917914177, "score": 1.7977004241041845, "task_avg": 10.052053743080329 }, { "model": "alibiserikbay__JevK5-Lite", "borda": 16.11922141119221, "noul": 3.76654702738377, "choice": 17.7797951838272, "score": 1.5654975915267526, "task_avg": 7.703946600912574 }, { "model": "franckverrot__lev-350m", "borda": 16.117531765341983, "noul": 5.935991628257736, "choice": 16.405108374637887, "score": 2.3352033016494516, "task_avg": 8.225434434848358 }, { "model": "Contrastive-LM__CLM-v0.1-8B", "borda": 16.014463368477966, "noul": 14.412694524927733, "choice": 5.857365116987648, "score": 1.1908580239087454, "task_avg": 7.153639221941376 }, { "model": "knowledgator__gliformer-large-v1", "borda": 16.00770478507705, "noul": 11.484628873458307, "choice": 13.644376375042802, "score": 0.7360329168838754, "task_avg": 8.621679388461661 }, { "model": "jerichosiahaya__Naluri-308M-encoder", "borda": 15.89449851311165, "noul": 9.151701070343478, "choice": 12.348336262914215, "score": 2.103617106215122, "task_avg": 7.867884813157605 }, { "model": "fastino__GLiNER2.5-Decide", "borda": 15.82691267910246, "noul": 5.400377848791741, "choice": 18.19382225695684, "score": 3.86811588722709, "task_avg": 9.154105330991891 }, { "model": "zeredy879__minojev", "borda": 15.573465801567995, "noul": 8.56832688483775, "choice": 14.56405132767957, "score": 0.6714324571009406, "task_avg": 7.93460355653942 }, { "model": "MoritzLaurer__ModernBERT-large-zeroshot-v2.0", "borda": 15.48560421735604, "noul": 7.331183111706821, "choice": 17.666254986073167, "score": 3.6760704109207163, "task_avg": 9.557836169566901 }, { "model": "fastino__gliner2.5-base-v1", "borda": 15.304812111381457, "noul": 8.439469009276774, "choice": 14.47523737644395, "score": 2.022515426402544, "task_avg": 8.312407270707755 }, { "model": "fastino__gliner2.5-small-v1", "borda": 14.61036766693701, "noul": 8.561408258769246, "choice": 9.659802627656926, "score": 0.8577162506172501, "task_avg": 6.359642379014472 }, { "model": "fastino__gliner2-large-v1", "borda": 14.147404703974049, "noul": 4.573740815952506, "choice": 14.246141445359422, "score": 3.502160455974361, "task_avg": 7.440680905762097 }, { "model": "DangerLabs__DM-JEPA", "borda": 13.632062719653959, "noul": 2.3453534688748725, "choice": 7.5740133411342665, "score": 0.05678259971611506, "task_avg": 3.325383136575085 }, { "model": "Manav2op__verdict-small", "borda": 13.422546634225467, "noul": 2.9023875492083064, "choice": 14.789408809054272, "score": 0.20211982269648562, "task_avg": 5.964638726986355 }, { "model": "heman10x__rlcd-modernbert-151m", "borda": 13.177547985942146, "noul": 2.4589584837028946, "choice": 15.542087739556877, "score": 1.572045506770059, "task_avg": 6.524363910009943 }, { "model": "notnotsamuel__LFM2.5-350M-RLCD", "borda": 12.270208164368748, "noul": 3.4312751472189125, "choice": 1.3549197108162505, "score": 1.262619370781004, "task_avg": 2.016271409605389 }, { "model": "mixedbread-ai__mxbai-rerank-base-v2", "borda": 11.930589348472559, "noul": 2.0324865897741966, "choice": 7.946053526070839, "score": 0.0, "task_avg": 3.326180038615012 }, { "model": "Alibaba-NLP__gte-reranker-modernbert-base", "borda": 11.687280346039469, "noul": 1.4893808110867344, "choice": 2.654646587771311, "score": 0.0, "task_avg": 1.3813424662860152 }, { "model": "fastino__gliner2.5-multi-v1", "borda": 11.63490132468235, "noul": 3.0257346247767076, "choice": 6.470804851610941, "score": 0.2718941682039498, "task_avg": 3.256144548197199 }, { "model": "Cactus-Compute__needle3", "borda": 11.37638550959719, "noul": 2.8042359077246624, "choice": 0.6742908467164807, "score": 0.0, "task_avg": 1.1595089181470475 }, { "model": "samatv256__mini-Jev", "borda": 10.781630170316305, "noul": 1.5711299855670875, "choice": 5.736470461187357, "score": 0.1576189245062373, "task_avg": 2.4884064570868945 }, { "model": "altslate__certo-decision-model", "borda": 10.676872127602058, "noul": 1.4496767390820329, "choice": 0.33999465537549906, "score": 0.007202716928625794, "task_avg": 0.5989580371287192 } ] }
{
"dataset": "hotchpotch/S1MB-english-v1@10bcb8c6",
"benchmarks": 137,
"borda_benchmarks": 137,
"cohort": 217,
"rescore_check": [
{
"model": "5ak3t__scm_max_14b_v0",
"benchmarks_checked": 16,
"max_abs_diff": 1.1102230246251565e-16
},
{
"model": "5ak3t__scm_max_14b_v1",
"benchmarks_checked": 16,
"max_abs_diff": 4.440892098500626e-16
},
{
"model": "5ak3t__scm_mid_4b_v1",
"benchmarks_checked": 16,
"max_abs_diff": 5.551115123125783e-16
}
],
"ours": {
"base": {
"temps": {
"choice": 1.707683209388825,
"noul": 2.4105066990845945,
"score": 1.2847580560947693
},
"raw": {
"adjusted": {
"aegis2-noul-test-v1": 0.42052313883299797,
"laya--ag-news-choice-test-v1": 0.7910447761194032,
"aqua-rat-choice-test-v1": 0.042253521126760604,
"arc-choice-test-v1": 0.8823529411764708,
"arct-choice-test-v1": 0.2765957446808511,
"argument-quality-choice-test-v1": 0.28571428571428575,
"argument-quality-noul-test-v1": 0.09289526462740527,
"babi-nli-noul-test-v1": 0.10000000000000009,
"banking77-choice-test-v1": 0.631578947368421,
"bbq-choice-test-v1": 0.8999999999999999,
"boardgameqa-choice-test-v1": 0.25000000000000006,
"canttalk-noul-test-v1": 0.7200000000000002,
"civil-comments-noul-test-v1": 0.3041383169192424,
"cladder-noul-test-v1": 0.040000000000000036,
"clinc-choice-test-v1": 0.7931034482758621,
"contract-nli-choice-test-v1": 0.5173535791757051,
"corr2cause-choice-test-v1": 0.0,
"creak-noul-test-v1": 0.72,
"crows-pairs-choice-test-v1": 0.43749999999999994,
"dbpedia-choice-test-v1": 0.9775280898876404,
"defeasible-nli-choice-test-v1": 0.41304347826086946,
"laya--enron-spam-noul-test-v1": 0.76,
"esci-choice-test-v1": 0.0821917808219178,
"ethics-choice-test-v1": 0.5000000000000001,
"ethics-noul-test-v1": 0.1595238095238094,
"ethos-noul-test-v1": 0.45999999999999996,
"few-nerd-choice-test-v1": 0.6451612903225806,
"fol-nli-choice-test-v1": 0.16393442622950816,
"followir-core17-noul-test-v1": 0.26398601398601396,
"followir-news21-noul-test-v1": 0.03333333333333344,
"followir-robust04-noul-test-v1": 0.4736842105263157,
"go-emotions-noul-test-v1": 0.3630486674285902,
"gretel-pii-choice-test-v1": 0.6688311688311688,
"gsm8k-choice-test-v1": 0.12857142857142861,
"hans-noul-test-v1": 0.5,
"hatecheck-noul-test-v1": 0.72,
"hh-rlhf-choice-test-v1": 0.07692307692307698,
"hwu64-choice-test-v1": 0.797872340425532,
"impli-noul-test-v1": 0.28,
"lexcomp-noul-test-v1": 0.3799999999999999,
"logical-entailment-noul-test-v1": 0.040000000000000036,
"lonli-choice-test-v1": 0.540983606557377,
"massive-choice-test-v1": 0.7806215722120659,
"miqa-choice-test-v1": 0.7272727272727273,
"mtop-choice-test-v1": 0.74873660804528,
"nlsat-noul-test-v1": 0.0,
"open-jev--amount-extraction-control-v1-choice-test-v1": 0.5294117647058824,
"open-jev--amount-extraction-control-v1-noul-test-v1": 0.0,
"open-jev--browser-control-v1-choice-test-v1": 1.0,
"open-jev--citation-control-v1-choice-test-v1": 0.6363636363636365,
"open-jev--context-retention-control-v1-noul-test-v1": 0.0,
"open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391,
"open-jev--customer-control-v1-noul-test-v1": 0.75,
"open-jev--customer-control-v1-score-test-v1": 0.39788644560460573,
"open-jev--drone-control-v1-choice-test-v1": 0.0,
"open-jev--drone-control-v1-noul-test-v1": 0.0,
"open-jev--drone-control-v1-score-test-v1": 0.0,
"open-jev--email-selection-control-v1-choice-test-v1": 0.0,
"open-jev--email-selection-control-v1-noul-test-v1": 0.5,
"open-jev--entity-alignment-control-v1-noul-test-v1": 0.0,
"open-jev--entity-alignment-control-v1-score-test-v1": 0.0,
"open-jev--ir-control-v1-choice-test-v1": 0.6799999999999998,
"open-jev--ir-control-v1-noul-test-v1": 0.5714285714285714,
"open-jev--ir-control-v1-score-test-v1": 0.0,
"open-jev--mailroom-control-v1-choice-test-v1": 1.0,
"open-jev--mailroom-control-v1-noul-test-v1": 0.7305555555555556,
"open-jev--painting-geometry-v1-choice-test-v1": 0.5263157894736842,
"open-jev--painting-geometry-v1-noul-test-v1": 0.1333333333333333,
"open-jev--painting-geometry-v1-score-test-v1": 0.13055902085337423,

Xet Storage Details

Size:
141 kB
·
Xet hash:
782745c22b3866749875afc1f42488bff5d5f664940d74766192da6a07c3c3a0

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.