{ "benchmark": "RuBench v1", "split": "dev", "n_answers": 200, "n_criteria": 604, "built_at": "2026-11-04T00:15:58", "conditions": "first turn (feedback_mode=hint_1, reveal_requested=false, history=[]), no JSON schema enforcement, invalid JSON counts as wrong. RuBio: SYSTEM_PROMPT only; base and general models: SYSTEM_PROMPT+POLICY. RuBio and Qwen base: temperature 0, max_tokens 1024, thinking off. General models: vendor CLI at the listed reasoning effort, one fixed run.", "panel": { "round1": [ "gpt", "opus", "grok" ], "round2": [ "gpt", "opus", "gemini" ], "student_answer_author": "gemini" }, "caveats": [ "GPT and Opus were round-1 gold panelists: the r1-3/3 tier (521 of 604 dev criteria) contains their own blind judgments, so their scores include self-agreement and are upper bounds.", "Round-2 majority (r2-2/3) items include GPT, Opus and Gemini votes; see criterion_acc_excl_r2_2of3.", "Gemini wrote the synthetic student answers with intended labels; reported as reference only (DESIGN 4-1).", "Grok 4.7 (round-1 panelist) was not evaluated as a model.", "RuBio-27B is the RuIso-v6 retrain (main since 2026-11-04), run on a RunPod A100 Pod with vLLM 0.32.0 under the same generation settings; RuBio-4B v2 was run on RunPod Serverless (worker-v1-vllm, vLLM 0.32.0). The decision to replace the 27B main weights used this same dev split." ], "models": { "4b": { "key": "4b", "label": "RuBio-4B v2", "hf": "mulkzz/RuBio-4B@ba9e00c8", "role": "finetuned", "size": "4B", "name": "RuBio-4B v2", "answers": 200, "missing_output": 0, "json_invalid": 0, "criterion_acc": { "mean": 0.7716666666666667, "ci95": [ 0.7339481076683567, 0.8093852256649767 ], "n_answers": 200 }, "criterion_acc_excl_r2_2of3": { "mean": 0.79875, "ci95": [ 0.759669235815335, 0.837830764184665 ], "n_answers": 200 }, "criterion_micro": { "hit": 467, "n": 604 }, "misconception": { "k": 106, "n": 133, "p": 0.7969924812030075, "ci95": [ 0.7207474553277116, 0.8565630300901761 ] }, "misconception_with_id": { "k": 65, "n": 79, "p": 0.8227848101265823, "ci95": [ 0.7242382665030478, 0.8913956243248582 ] }, "json_valid": { "k": 200, "n": 200, "p": 1.0, "ci95": [ 0.981154748802476, 1.0 ] }, "unit_criterion_micro": { "I": { "k": 156, "n": 206, "p": 0.7572815533980582, "ci95": [ 0.6943735885025178, 0.8107697158073134 ] }, "II": { "k": 154, "n": 200, "p": 0.77, "ci95": [ 0.7069170932155301, 0.822906471137807 ] }, "III": { "k": 157, "n": 198, "p": 0.7929292929292929, "ci95": [ 0.7311760804230768, 0.8435324539592243 ] } }, "other_issues": { "k": 153, "n": 200, "p": 0.765, "ci95": [ 0.7015864484736013, 0.8184255683917109 ] }, "answer_status": { "k": 124, "n": 200, "p": 0.62, "ci95": [ 0.5510673223171103, 0.684409817395484 ] }, "gold_tier_criterion_acc": { "r1-3/3": { "k": 431, "n": 521, "p": 0.8272552783109405, "ci95": [ 0.7924302993782009, 0.8572897340091328 ] }, "r2-3/3": { "k": 10, "n": 23, "p": 0.43478260869565216, "ci95": [ 0.2563466486442807, 0.6318858887246053 ] }, "r2-2/3": { "k": 23, "n": 51, "p": 0.45098039215686275, "ci95": [ 0.32267542174059904, 0.5861526522832785 ] }, "human": { "k": 3, "n": 9, "p": 0.3333333333333333, "ci95": [ 0.12058406396498972, 0.6457973346907151 ] } }, "other_issues_split": { "has_error_recall": { "k": 10, "n": 53, "p": 0.18867924528301888, "ci95": [ 0.10585337627628057, 0.3135843061386674 ] }, "no_error_specificity": { "k": 143, "n": 147, "p": 0.9727891156462585, "ci95": [ 0.9321289915585997, 0.9893684235398896 ] } }, "confusion": { "contradicted->contradicted": 121, "contradicted->missing": 5, "contradicted->supported": 3, "contradicted->unclear": 4, "missing->contradicted": 12, "missing->missing": 92, "missing->supported": 18, "missing->unclear": 20, "supported->contradicted": 14, "supported->missing": 9, "supported->supported": 232, "supported->unclear": 28, "unclear->contradicted": 8, "unclear->missing": 7, "unclear->supported": 9, "unclear->unclear": 22 }, "cli_seconds_p50": null }, "qwen4b": { "key": "qwen4b", "label": "Qwen3.5-4B (base)", "hf": "Qwen/Qwen3.5-4B", "role": "base", "size": "4B", "name": "Qwen3.5-4B (기본)", "answers": 200, "missing_output": 0, "json_invalid": 0, "criterion_acc": { "mean": 0.7091666666666667, "ci95": [ 0.673031876586196, 0.7453014567471374 ], "n_answers": 200 }, "criterion_acc_excl_r2_2of3": { "mean": 0.7454166666666667, "ci95": [ 0.7095199602308042, 0.7813133731025292 ], "n_answers": 200 }, "criterion_micro": { "hit": 427, "n": 604 }, "misconception": { "k": 78, "n": 133, "p": 0.5864661654135338, "ci95": [ 0.501491500687543, 0.666586235573361 ] }, "misconception_with_id": { "k": 55, "n": 79, "p": 0.6962025316455697, "ci95": [ 0.5876536225817802, 0.7865552130194958 ] }, "json_valid": { "k": 200, "n": 200, "p": 1.0, "ci95": [ 0.981154748802476, 1.0 ] }, "unit_criterion_micro": { "I": { "k": 144, "n": 206, "p": 0.6990291262135923, "ci95": [ 0.633218801872325, 0.7575524335371671 ] }, "II": { "k": 142, "n": 200, "p": 0.71, "ci95": [ 0.6436253597813291, 0.7684596347157107 ] }, "III": { "k": 141, "n": 198, "p": 0.7121212121212122, "ci95": [ 0.6454906562919455, 0.770677592743514 ] } }, "other_issues": { "k": 150, "n": 200, "p": 0.75, "ci95": [ 0.6856591553575013, 0.8049182190437367 ] }, "answer_status": { "k": 89, "n": 200, "p": 0.445, "ci95": [ 0.37780614202227114, 0.5142668356094566 ] }, "gold_tier_criterion_acc": { "r1-3/3": { "k": 402, "n": 521, "p": 0.7715930902111324, "ci95": [ 0.7336347625660318, 0.8055757050252159 ] }, "r2-3/3": { "k": 4, "n": 23, "p": 0.17391304347826086, "ci95": [ 0.06978666088359675, 0.37137602596083263 ] }, "r2-2/3": { "k": 15, "n": 51, "p": 0.29411764705882354, "ci95": [ 0.1870874425221019, 0.4299904683781837 ] }, "human": { "k": 6, "n": 9, "p": 0.6666666666666666, "ci95": [ 0.35420266530928485, 0.8794159360350102 ] } }, "other_issues_split": { "has_error_recall": { "k": 4, "n": 53, "p": 0.07547169811320754, "ci95": [ 0.029739608356547, 0.17858450402747283 ] }, "no_error_specificity": { "k": 146, "n": 147, "p": 0.9931972789115646, "ci95": [ 0.9624761437110765, 0.9987981382261968 ] } }, "confusion": { "contradicted->contradicted": 100, "contradicted->missing": 20, "contradicted->supported": 10, "contradicted->unclear": 3, "missing->contradicted": 22, "missing->missing": 79, "missing->supported": 37, "missing->unclear": 4, "supported->contradicted": 12, "supported->missing": 16, "supported->supported": 244, "supported->unclear": 11, "unclear->contradicted": 7, "unclear->missing": 9, "unclear->supported": 26, "unclear->unclear": 4 }, "cli_seconds_p50": null }, "27b": { "key": "27b", "src": "27b-v6-s3407", "label": "RuBio-27B", "hf": "mulkzz/RuBio-27B@c1cfefdb", "role": "finetuned", "size": "27B", "name": "RuBio-27B RuIso-v6 (시드 3407)", "answers": 200, "missing_output": 0, "json_invalid": 0, "criterion_acc": { "mean": 0.86875, "ci95": [ 0.8381287620959553, 0.8993712379040447 ], "n_answers": 200 }, "criterion_acc_excl_r2_2of3": { "mean": 0.9, "ci95": [ 0.8714503967862466, 0.9285496032137535 ], "n_answers": 200 }, "criterion_micro": { "hit": 524, "n": 604 }, "misconception": { "k": 118, "n": 133, "p": 0.8872180451127819, "ci95": [ 0.8222450524506153, 0.9304508968916938 ] }, "misconception_with_id": { "k": 73, "n": 79, "p": 0.9240506329113924, "ci95": [ 0.8440460366216044, 0.9647278983876056 ] }, "json_valid": { "k": 200, "n": 200, "p": 1.0, "ci95": [ 0.981154748802476, 1.0 ] }, "unit_criterion_micro": { "I": { "k": 185, "n": 206, "p": 0.8980582524271845, "ci95": [ 0.8491894424118119, 0.9323530284071725 ] }, "II": { "k": 166, "n": 200, "p": 0.83, "ci95": [ 0.7718412936135373, 0.8757208405960968 ] }, "III": { "k": 173, "n": 198, "p": 0.8737373737373737, "ci95": [ 0.8202540537968194, 0.9129947659323233 ] } }, "other_issues": { "k": 173, "n": 200, "p": 0.865, "ci95": [ 0.810708740295804, 0.9055342263300035 ] }, "answer_status": { "k": 154, "n": 200, "p": 0.77, "ci95": [ 0.7069170932155301, 0.822906471137807 ] }, "gold_tier_criterion_acc": { "r1-3/3": { "k": 483, "n": 521, "p": 0.927063339731286, "ci95": [ 0.9014725811198147, 0.9464025357639493 ] }, "r2-3/3": { "k": 11, "n": 23, "p": 0.4782608695652174, "ci95": [ 0.29237189265791597, 0.670372286465046 ] }, "r2-2/3": { "k": 23, "n": 51, "p": 0.45098039215686275, "ci95": [ 0.32267542174059904, 0.5861526522832785 ] }, "human": { "k": 7, "n": 9, "p": 0.7777777777777778, "ci95": [ 0.45258959147532657, 0.9367747440984988 ] } }, "other_issues_split": { "has_error_recall": { "k": 46, "n": 53, "p": 0.8679245283018868, "ci95": [ 0.7515977273649117, 0.9345213752356045 ] }, "no_error_specificity": { "k": 127, "n": 147, "p": 0.8639455782312925, "ci95": [ 0.7991850746700077, 0.9101690506216352 ] } }, "confusion": { "contradicted->contradicted": 127, "contradicted->missing": 4, "contradicted->supported": 1, "contradicted->unclear": 1, "missing->contradicted": 8, "missing->missing": 125, "missing->supported": 2, "missing->unclear": 7, "supported->contradicted": 4, "supported->missing": 20, "supported->supported": 253, "supported->unclear": 6, "unclear->contradicted": 4, "unclear->missing": 15, "unclear->supported": 8, "unclear->unclear": 19 }, "cli_seconds_p50": null }, "qwen27b": { "key": "qwen27b", "label": "Qwen3.8-27B (base)", "hf": "Qwen/Qwen3.8-27B", "role": "base", "size": "27B", "name": "Qwen3.8-27B (기본)", "answers": 200, "missing_output": 0, "json_invalid": 5, "criterion_acc": { "mean": 0.8179166666666667, "ci95": [ 0.7816876269997497, 0.8541457063335838 ], "n_answers": 200 }, "criterion_acc_excl_r2_2of3": { "mean": 0.8495833333333332, "ci95": [ 0.8142417703596521, 0.8849248963070144 ], "n_answers": 200 }, "criterion_micro": { "hit": 495, "n": 604 }, "misconception": { "k": 107, "n": 133, "p": 0.8045112781954887, "ci95": [ 0.7289698915278552, 0.8629560492170677 ] }, "misconception_with_id": { "k": 68, "n": 79, "p": 0.8607594936708861, "ci95": [ 0.7676269042027796, 0.9204345031931153 ] }, "json_valid": { "k": 195, "n": 200, "p": 0.975, "ci95": [ 0.9428217485145032, 0.989275262847849 ] }, "unit_criterion_micro": { "I": { "k": 165, "n": 206, "p": 0.8009708737864077, "ci95": [ 0.7411592356541727, 0.8497631203309128 ] }, "II": { "k": 167, "n": 200, "p": 0.835, "ci95": [ 0.777342313757747, 0.8800313679399118 ] }, "III": { "k": 163, "n": 198, "p": 0.8232323232323232, "ci95": [ 0.764095715325512, 0.8700654260618547 ] } }, "other_issues": { "k": 156, "n": 200, "p": 0.78, "ci95": [ 0.7176121367571497, 0.8318345225722368 ] }, "answer_status": { "k": 120, "n": 200, "p": 0.6, "ci95": [ 0.530836862213719, 0.6653940875467761 ] }, "gold_tier_criterion_acc": { "r1-3/3": { "k": 461, "n": 521, "p": 0.8848368522072937, "ci95": [ 0.854565276901407, 0.9094749969646364 ] }, "r2-3/3": { "k": 5, "n": 23, "p": 0.21739130434782608, "ci95": [ 0.09663993783788177, 0.4190343907606237 ] }, "r2-2/3": { "k": 24, "n": 51, "p": 0.47058823529411764, "ci95": [ 0.3405301441444071, 0.6047667002699194 ] }, "human": { "k": 5, "n": 9, "p": 0.5555555555555556, "ci95": [ 0.26665173025527866, 0.8112211368594864 ] } }, "other_issues_split": { "has_error_recall": { "k": 29, "n": 53, "p": 0.5471698113207547, "ci95": [ 0.41454001247278066, 0.6734239750401059 ] }, "no_error_specificity": { "k": 127, "n": 147, "p": 0.8639455782312925, "ci95": [ 0.7991850746700077, 0.9101690506216352 ] } }, "confusion": { "contradicted->(없음)": 6, "contradicted->contradicted": 112, "contradicted->missing": 7, "contradicted->supported": 5, "contradicted->unclear": 3, "missing->(없음)": 8, "missing->contradicted": 3, "missing->missing": 95, "missing->supported": 20, "missing->unclear": 16, "supported->(없음)": 3, "supported->contradicted": 4, "supported->missing": 1, "supported->supported": 269, "supported->unclear": 6, "unclear->(없음)": 1, "unclear->missing": 3, "unclear->supported": 23, "unclear->unclear": 19 }, "cli_seconds_p50": 9.7 }, "gpt": { "key": "gpt", "label": "GPT-6 Astra (xhigh)", "hf": null, "role": "general", "size": null, "name": "GPT-6 Astra (xhigh)", "answers": 200, "missing_output": 0, "json_invalid": 0, "criterion_acc": { "mean": 0.9116666666666667, "ci95": [ 0.8858637301001623, 0.9374696032331712 ], "n_answers": 200 }, "criterion_acc_excl_r2_2of3": { "mean": 0.9558333333333333, "ci95": [ 0.9362898427686828, 0.9753768238979839 ], "n_answers": 200 }, "criterion_micro": { "hit": 550, "n": 604 }, "misconception": { "k": 129, "n": 133, "p": 0.9699248120300752, "ci95": [ 0.9252225048958136, 0.9882434530438822 ] }, "misconception_with_id": { "k": 78, "n": 79, "p": 0.9873417721518988, "ci95": [ 0.9317244628529116, 0.9977619997696132 ] }, "json_valid": { "k": 200, "n": 200, "p": 1.0, "ci95": [ 0.981154748802476, 1.0 ] }, "unit_criterion_micro": { "I": { "k": 184, "n": 206, "p": 0.8932038834951457, "ci95": [ 0.8436020225775144, 0.928409442499775 ] }, "II": { "k": 185, "n": 200, "p": 0.925, "ci95": [ 0.8799564990407998, 0.9540250374413048 ] }, "III": { "k": 181, "n": 198, "p": 0.9141414141414141, "ci95": [ 0.866814758905608, 0.9457042034969555 ] } }, "other_issues": { "k": 177, "n": 200, "p": 0.885, "ci95": [ 0.8333529508707886, 0.9221362057071179 ] }, "answer_status": { "k": 176, "n": 200, "p": 0.88, "ci95": [ 0.8276575999704266, 0.9180200091194551 ] }, "gold_tier_criterion_acc": { "r1-3/3": { "k": 510, "n": 521, "p": 0.9788867562380038, "ci95": [ 0.9625927664904859, 0.9881705668241167 ] }, "r2-3/3": { "k": 14, "n": 23, "p": 0.6086956521739131, "ci95": [ 0.4078556031551567, 0.7784235012300337 ] }, "r2-2/3": { "k": 22, "n": 51, "p": 0.43137254901960786, "ci95": [ 0.30501259121603025, 0.5673467124173983 ] }, "human": { "k": 4, "n": 9, "p": 0.4444444444444444, "ci95": [ 0.18877886314051356, 0.7333482697447213 ] } }, "other_issues_split": { "has_error_recall": { "k": 33, "n": 53, "p": 0.6226415094339622, "ci95": [ 0.48806923125215484, 0.7406371362813504 ] }, "no_error_specificity": { "k": 144, "n": 147, "p": 0.9795918367346939, "ci95": [ 0.9417208980015789, 0.9930354727098384 ] } }, "confusion": { "contradicted->contradicted": 129, "contradicted->missing": 3, "contradicted->unclear": 1, "missing->contradicted": 1, "missing->missing": 135, "missing->supported": 2, "missing->unclear": 4, "supported->contradicted": 3, "supported->missing": 11, "supported->supported": 269, "unclear->contradicted": 2, "unclear->missing": 23, "unclear->supported": 4, "unclear->unclear": 17 }, "cli_seconds_p50": 575.6 }, "opus": { "key": "opus", "label": "Claude Opus 5.5 (xhigh)", "hf": null, "role": "general", "size": null, "name": "Claude Opus 5.5 (xhigh)", "answers": 200, "missing_output": 0, "json_invalid": 0, "criterion_acc": { "mean": 0.9420833333333333, "ci95": [ 0.9203542491963614, 0.9638124174703051 ], "n_answers": 200 }, "criterion_acc_excl_r2_2of3": { "mean": 0.9608333333333333, "ci95": [ 0.9417409178385642, 0.9799257488281025 ], "n_answers": 200 }, "criterion_micro": { "hit": 570, "n": 604 }, "misconception": { "k": 127, "n": 133, "p": 0.9548872180451128, "ci95": [ 0.9050722874953598, 0.9791627597902657 ] }, "misconception_with_id": { "k": 77, "n": 79, "p": 0.9746835443037974, "ci95": [ 0.9123143405749654, 0.9930296165248962 ] }, "json_valid": { "k": 200, "n": 200, "p": 1.0, "ci95": [ 0.981154748802476, 1.0 ] }, "unit_criterion_micro": { "I": { "k": 193, "n": 206, "p": 0.9368932038834952, "ci95": [ 0.895037892168079, 0.9627526245844646 ] }, "II": { "k": 189, "n": 200, "p": 0.945, "ci95": [ 0.9042131036406227, 0.9690146227935807 ] }, "III": { "k": 188, "n": 198, "p": 0.9494949494949495, "ci95": [ 0.9095419269028148, 0.9723384103389922 ] } }, "other_issues": { "k": 195, "n": 200, "p": 0.975, "ci95": [ 0.9428217485145032, 0.989275262847849 ] }, "answer_status": { "k": 184, "n": 200, "p": 0.92, "ci95": [ 0.8740106225357106, 0.9501593664583693 ] }, "gold_tier_criterion_acc": { "r1-3/3": { "k": 510, "n": 521, "p": 0.9788867562380038, "ci95": [ 0.9625927664904859, 0.9881705668241167 ] }, "r2-3/3": { "k": 18, "n": 23, "p": 0.782608695652174, "ci95": [ 0.5809656092393763, 0.9033600621621182 ] }, "r2-2/3": { "k": 37, "n": 51, "p": 0.7254901960784313, "ci95": [ 0.5905337813556237, 0.8288570781345395 ] }, "human": { "k": 5, "n": 9, "p": 0.5555555555555556, "ci95": [ 0.26665173025527866, 0.8112211368594864 ] } }, "other_issues_split": { "has_error_recall": { "k": 52, "n": 53, "p": 0.9811320754716981, "ci95": [ 0.9005711355345968, 0.9966615370968476 ] }, "no_error_specificity": { "k": 143, "n": 147, "p": 0.9727891156462585, "ci95": [ 0.9321289915585997, 0.9893684235398896 ] } }, "confusion": { "contradicted->contradicted": 128, "contradicted->missing": 3, "contradicted->supported": 1, "contradicted->unclear": 1, "missing->contradicted": 1, "missing->missing": 123, "missing->supported": 7, "missing->unclear": 11, "supported->missing": 3, "supported->supported": 279, "supported->unclear": 1, "unclear->supported": 6, "unclear->unclear": 40 }, "cli_seconds_p50": 41.3 }, "gemini": { "key": "gemini", "label": "Gemini 4 Argon (High)", "hf": null, "role": "reference", "size": null, "name": "Gemini 4 Argon (High)", "answers": 200, "missing_output": 0, "json_invalid": 2, "criterion_acc": { "mean": 0.9125, "ci95": [ 0.8850333281496484, 0.9399666718503515 ], "n_answers": 200 }, "criterion_acc_excl_r2_2of3": { "mean": 0.9358333333333333, "ci95": [ 0.9098731921940174, 0.9617934744726492 ], "n_answers": 200 }, "criterion_micro": { "hit": 551, "n": 604 }, "misconception": { "k": 122, "n": 133, "p": 0.9172932330827067, "ci95": [ 0.8579662495837602, 0.9531915210666896 ] }, "misconception_with_id": { "k": 75, "n": 79, "p": 0.9493670886075949, "ci95": [ 0.8769230243999817, 0.980135921654554 ] }, "json_valid": { "k": 198, "n": 200, "p": 0.99, "ci95": [ 0.9642783183248235, 0.997253335501603 ] }, "unit_criterion_micro": { "I": { "k": 187, "n": 206, "p": 0.9077669902912622, "ci95": [ 0.8604469235517486, 0.9401575587506256 ] }, "II": { "k": 184, "n": 200, "p": 0.92, "ci95": [ 0.8740106225357106, 0.9501593664583693 ] }, "III": { "k": 180, "n": 198, "p": 0.9090909090909091, "ci95": [ 0.8608883910901738, 0.9417218034782121 ] } }, "other_issues": { "k": 190, "n": 200, "p": 0.95, "ci95": [ 0.9104219523342212, 0.9726173215880072 ] }, "answer_status": { "k": 179, "n": 200, "p": 0.895, "ci95": [ 0.8448197976153835, 0.9302924539385726 ] }, "gold_tier_criterion_acc": { "r1-3/3": { "k": 496, "n": 521, "p": 0.9520153550863724, "ci95": [ 0.9301245809465594, 0.9672893068113121 ] }, "r2-3/3": { "k": 19, "n": 23, "p": 0.8260869565217391, "ci95": [ 0.6286239740391674, 0.9302133391164032 ] }, "r2-2/3": { "k": 32, "n": 51, "p": 0.6274509803921569, "ci95": [ 0.49025241212438464, 0.7467945954135337 ] }, "human": { "k": 4, "n": 9, "p": 0.4444444444444444, "ci95": [ 0.18877886314051356, 0.7333482697447213 ] } }, "other_issues_split": { "has_error_recall": { "k": 45, "n": 53, "p": 0.8490566037735849, "ci95": [ 0.7294577896504801, 0.9214757179448814 ] }, "no_error_specificity": { "k": 145, "n": 147, "p": 0.9863945578231292, "ci95": [ 0.9517544022691328, 0.9962609240552124 ] } }, "confusion": { "contradicted->contradicted": 125, "contradicted->missing": 5, "contradicted->supported": 1, "contradicted->unclear": 2, "missing->(없음)": 2, "missing->missing": 125, "missing->supported": 10, "missing->unclear": 5, "supported->(없음)": 3, "supported->contradicted": 2, "supported->missing": 6, "supported->supported": 267, "supported->unclear": 5, "unclear->(없음)": 1, "unclear->contradicted": 1, "unclear->missing": 9, "unclear->supported": 1, "unclear->unclear": 34 }, "cli_seconds_p50": 87.9 } }, "paired": { "qwen4b-minus-4b": { "all": { "diff": -0.06250000000000001, "ci95": [ -0.09929215430834135, -0.02570784569165868 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.05333333333333334, "ci95": [ -0.0949195943790324, -0.011747072287634275 ], "n": 200, "verdict": "악화" } }, "27b-minus-4b": { "all": { "diff": 0.09708333333333334, "ci95": [ 0.06123184381518337, 0.1329348228514833 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.10125, "ci95": [ 0.06521017094468781, 0.1372898290553122 ], "n": 200, "verdict": "개선" } }, "qwen27b-minus-4b": { "all": { "diff": 0.04625, "ci95": [ 0.007906503441078273, 0.08459349655892173 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.05083333333333334, "ci95": [ 0.008389559707535299, 0.09327710695913138 ], "n": 200, "verdict": "개선" } }, "gpt-minus-4b": { "all": { "diff": 0.14, "ci95": [ 0.1028811816212637, 0.17711881837873633 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.15708333333333335, "ci95": [ 0.11841813107448726, 0.19574853559217945 ], "n": 200, "verdict": "개선" } }, "opus-minus-4b": { "all": { "diff": 0.1704166666666667, "ci95": [ 0.1349501475307221, 0.20588318580261128 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.16208333333333336, "ci95": [ 0.12777146352786023, 0.19639520313880648 ], "n": 200, "verdict": "개선" } }, "gemini-minus-4b": { "all": { "diff": 0.14083333333333334, "ci95": [ 0.10129028178518129, 0.18037638488148539 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.13708333333333333, "ci95": [ 0.0986490412756628, 0.17551762539100385 ], "n": 200, "verdict": "개선" } }, "4b-minus-qwen4b": { "all": { "diff": 0.06250000000000001, "ci95": [ 0.02570784569165868, 0.09929215430834135 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.05333333333333334, "ci95": [ 0.011747072287634275, 0.0949195943790324 ], "n": 200, "verdict": "개선" } }, "27b-minus-qwen4b": { "all": { "diff": 0.15958333333333333, "ci95": [ 0.12437326122557398, 0.1947934054410927 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.15458333333333335, "ci95": [ 0.11312043866157052, 0.1960462280050962 ], "n": 200, "verdict": "개선" } }, "qwen27b-minus-qwen4b": { "all": { "diff": 0.10875, "ci95": [ 0.06948238748995589, 0.1480176125100441 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.10416666666666669, "ci95": [ 0.06221595810731039, 0.14611737522602297 ], "n": 200, "verdict": "개선" } }, "gpt-minus-qwen4b": { "all": { "diff": 0.2025, "ci95": [ 0.16509784766297997, 0.23990215233702006 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.21041666666666667, "ci95": [ 0.1727924563143645, 0.24804087701896885 ], "n": 200, "verdict": "개선" } }, "opus-minus-qwen4b": { "all": { "diff": 0.2329166666666667, "ci95": [ 0.1962971271528449, 0.26953620618048846 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.21541666666666667, "ci95": [ 0.17708051297608593, 0.25375282035724744 ], "n": 200, "verdict": "개선" } }, "gemini-minus-qwen4b": { "all": { "diff": 0.20333333333333337, "ci95": [ 0.16215851002079762, 0.2445081566458691 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.19041666666666668, "ci95": [ 0.14755506490751477, 0.23327826842581859 ], "n": 200, "verdict": "개선" } }, "4b-minus-27b": { "all": { "diff": -0.09708333333333334, "ci95": [ -0.1329348228514833, -0.06123184381518337 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.10125, "ci95": [ -0.1372898290553122, -0.06521017094468781 ], "n": 200, "verdict": "악화" } }, "qwen4b-minus-27b": { "all": { "diff": -0.15958333333333333, "ci95": [ -0.1947934054410927, -0.12437326122557398 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.15458333333333335, "ci95": [ -0.1960462280050962, -0.11312043866157052 ], "n": 200, "verdict": "악화" } }, "qwen27b-minus-27b": { "all": { "diff": -0.05083333333333334, "ci95": [ -0.09092183669301501, -0.010744829973651678 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.05041666666666667, "ci95": [ -0.0903058270121205, -0.01052750632121284 ], "n": 200, "verdict": "악화" } }, "gpt-minus-27b": { "all": { "diff": 0.04291666666666667, "ci95": [ 0.01078839936599886, 0.07504493396733448 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.05583333333333334, "ci95": [ 0.02437694687489072, 0.08728971979177597 ], "n": 200, "verdict": "개선" } }, "opus-minus-27b": { "all": { "diff": 0.07333333333333333, "ci95": [ 0.04152834968415308, 0.10513831698251358 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.060833333333333336, "ci95": [ 0.030981954682252844, 0.09068471198441383 ], "n": 200, "verdict": "개선" } }, "gemini-minus-27b": { "all": { "diff": 0.04375, "ci95": [ 0.009717845060980758, 0.07778215493901924 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.035833333333333335, "ci95": [ 0.001730887172231424, 0.06993577949443525 ], "n": 200, "verdict": "개선" } }, "4b-minus-qwen27b": { "all": { "diff": -0.04625, "ci95": [ -0.08459349655892173, -0.007906503441078273 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.05083333333333334, "ci95": [ -0.09327710695913138, -0.008389559707535299 ], "n": 200, "verdict": "악화" } }, "qwen4b-minus-qwen27b": { "all": { "diff": -0.10875, "ci95": [ -0.1480176125100441, -0.06948238748995589 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.10416666666666669, "ci95": [ -0.14611737522602297, -0.06221595810731039 ], "n": 200, "verdict": "악화" } }, "27b-minus-qwen27b": { "all": { "diff": 0.05083333333333334, "ci95": [ 0.010744829973651678, 0.09092183669301501 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.05041666666666667, "ci95": [ 0.01052750632121284, 0.0903058270121205 ], "n": 200, "verdict": "개선" } }, "gpt-minus-qwen27b": { "all": { "diff": 0.09375, "ci95": [ 0.05730219163645278, 0.13019780836354722 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.10625, "ci95": [ 0.07279390330302032, 0.13970609669697967 ], "n": 200, "verdict": "개선" } }, "opus-minus-qwen27b": { "all": { "diff": 0.12416666666666668, "ci95": [ 0.09197561056896073, 0.15635772276437263 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.11125, "ci95": [ 0.07880409709964073, 0.14369590290035927 ], "n": 200, "verdict": "개선" } }, "gemini-minus-qwen27b": { "all": { "diff": 0.09458333333333334, "ci95": [ 0.0551882445624855, 0.13397842210418118 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.08625, "ci95": [ 0.04819286835030037, 0.12430713164969961 ], "n": 200, "verdict": "개선" } }, "4b-minus-gpt": { "all": { "diff": -0.14, "ci95": [ -0.17711881837873633, -0.1028811816212637 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.15708333333333335, "ci95": [ -0.19574853559217945, -0.11841813107448726 ], "n": 200, "verdict": "악화" } }, "qwen4b-minus-gpt": { "all": { "diff": -0.2025, "ci95": [ -0.23990215233702006, -0.16509784766297997 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.21041666666666667, "ci95": [ -0.24804087701896885, -0.1727924563143645 ], "n": 200, "verdict": "악화" } }, "27b-minus-gpt": { "all": { "diff": -0.04291666666666667, "ci95": [ -0.07504493396733448, -0.01078839936599886 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.05583333333333334, "ci95": [ -0.08728971979177597, -0.02437694687489072 ], "n": 200, "verdict": "악화" } }, "qwen27b-minus-gpt": { "all": { "diff": -0.09375, "ci95": [ -0.13019780836354722, -0.05730219163645278 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.10625, "ci95": [ -0.13970609669697967, -0.07279390330302032 ], "n": 200, "verdict": "악화" } }, "opus-minus-gpt": { "all": { "diff": 0.030416666666666668, "ci95": [ 0.004444457390938891, 0.056388875942394445 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.005000000000000001, "ci95": [ -0.015406897160101511, 0.025406897160101513 ], "n": 200, "verdict": "차이 없음" } }, "gemini-minus-gpt": { "all": { "diff": 0.0008333333333333328, "ci95": [ -0.029734282082786483, 0.03140094874945315 ], "n": 200, "verdict": "차이 없음" }, "no_majority": { "diff": -0.02, "ci95": [ -0.048200934523245254, 0.008200934523245256 ], "n": 200, "verdict": "차이 없음" } }, "4b-minus-opus": { "all": { "diff": -0.1704166666666667, "ci95": [ -0.20588318580261128, -0.1349501475307221 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.16208333333333336, "ci95": [ -0.19639520313880648, -0.12777146352786023 ], "n": 200, "verdict": "악화" } }, "qwen4b-minus-opus": { "all": { "diff": -0.2329166666666667, "ci95": [ -0.26953620618048846, -0.1962971271528449 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.21541666666666667, "ci95": [ -0.25375282035724744, -0.17708051297608593 ], "n": 200, "verdict": "악화" } }, "27b-minus-opus": { "all": { "diff": -0.07333333333333333, "ci95": [ -0.10513831698251358, -0.04152834968415308 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.060833333333333336, "ci95": [ -0.09068471198441383, -0.030981954682252844 ], "n": 200, "verdict": "악화" } }, "qwen27b-minus-opus": { "all": { "diff": -0.12416666666666668, "ci95": [ -0.15635772276437263, -0.09197561056896073 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.11125, "ci95": [ -0.14369590290035927, -0.07880409709964073 ], "n": 200, "verdict": "악화" } }, "gpt-minus-opus": { "all": { "diff": -0.030416666666666668, "ci95": [ -0.056388875942394445, -0.004444457390938891 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.005000000000000001, "ci95": [ -0.025406897160101513, 0.015406897160101511 ], "n": 200, "verdict": "차이 없음" } }, "gemini-minus-opus": { "all": { "diff": -0.029583333333333336, "ci95": [ -0.056084893999743986, -0.003081772666922687 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.025, "ci95": [ -0.04693792318061361, -0.003062076819386396 ], "n": 200, "verdict": "악화" } }, "4b-minus-gemini": { "all": { "diff": -0.14083333333333334, "ci95": [ -0.18037638488148539, -0.10129028178518129 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.13708333333333333, "ci95": [ -0.17551762539100385, -0.0986490412756628 ], "n": 200, "verdict": "악화" } }, "qwen4b-minus-gemini": { "all": { "diff": -0.20333333333333337, "ci95": [ -0.2445081566458691, -0.16215851002079762 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.19041666666666668, "ci95": [ -0.23327826842581859, -0.14755506490751477 ], "n": 200, "verdict": "악화" } }, "27b-minus-gemini": { "all": { "diff": -0.04375, "ci95": [ -0.07778215493901924, -0.009717845060980758 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.035833333333333335, "ci95": [ -0.06993577949443525, -0.001730887172231424 ], "n": 200, "verdict": "악화" } }, "qwen27b-minus-gemini": { "all": { "diff": -0.09458333333333334, "ci95": [ -0.13397842210418118, -0.0551882445624855 ], "n": 200, "verdict": "악화" }, "no_majority": { "diff": -0.08625, "ci95": [ -0.12430713164969961, -0.04819286835030037 ], "n": 200, "verdict": "악화" } }, "gpt-minus-gemini": { "all": { "diff": -0.0008333333333333328, "ci95": [ -0.03140094874945315, 0.029734282082786483 ], "n": 200, "verdict": "차이 없음" }, "no_majority": { "diff": 0.02, "ci95": [ -0.008200934523245256, 0.048200934523245254 ], "n": 200, "verdict": "차이 없음" } }, "opus-minus-gemini": { "all": { "diff": 0.029583333333333336, "ci95": [ 0.003081772666922687, 0.056084893999743986 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.025, "ci95": [ 0.003062076819386396, 0.04693792318061361 ], "n": 200, "verdict": "개선" } } }, "supplementary": { "qwen27b_system_prompt_only": { "label": "Qwen3.8-27B (base, SYSTEM_PROMPT only)", "criterion_acc": { "mean": 0.8433333333333333, "ci95": [ 0.8119954335270959, 0.8746712331395706 ], "n_answers": 200 }, "criterion_acc_excl_r2_2of3": { "mean": 0.8729166666666667, "ci95": [ 0.8426809286496472, 0.9031524046836862 ], "n_answers": 200 }, "json_invalid": 0, "paired_27b_minus_this": { "all": { "diff": 0.02541666666666667, "ci95": [ -0.009341613239777467, 0.06017494657311081 ], "n": 200, "verdict": "차이 없음" }, "no_majority": { "diff": 0.027083333333333334, "ci95": [ -0.008110744018988085, 0.062277410685654754 ], "n": 200, "verdict": "차이 없음" } } } } }