{ "benchmark": "RuBench v1", "split": "dev", "n_answers": 200, "n_criteria": 604, "built_at": "2026-11-04T00:14:40", "conditions": "first turn (feedback_mode=hint_1, reveal_requested=false, history=[]), temperature 0, max_tokens 1024, enable_thinking=false, no JSON schema enforcement. RuBio: SYSTEM_PROMPT only; base: SYSTEM_PROMPT+POLICY. Invalid JSON counts as wrong.", "finetuned": { "key": "9b-v6-s3408", "label": "RuBio-9B", "hf": "mulkzz/RuBio-9B@f61ac9cb", "in_dist_train_dev_criterion_match": 0.9743260590500642, "name": "RuBio-9B RuIso-v6 (시드 3408)", "answers": 200, "missing_output": 0, "json_invalid": 1, "criterion_acc": { "mean": 0.84875, "ci95": [ 0.8161433560231208, 0.8813566439768792 ], "n_answers": 200 }, "criterion_acc_excl_r2_2of3": { "mean": 0.8770833333333333, "ci95": [ 0.8464292781603502, 0.9077373885063165 ], "n_answers": 200 }, "criterion_micro": { "hit": 512, "n": 604 }, "misconception": { "k": 111, "n": 133, "p": 0.8345864661654135, "ci95": [ 0.7622364035210294, 0.888151358532034 ] }, "misconception_with_id": { "k": 65, "n": 79, "p": 0.8227848101265823, "ci95": [ 0.7242382665030478, 0.8913956243248582 ] }, "json_valid": { "k": 199, "n": 200, "p": 0.995, "ci95": [ 0.9722263725443985, 0.9991168287700527 ] }, "unit_criterion_micro": { "I": { "k": 170, "n": 206, "p": 0.8252427184466019, "ci95": [ 0.7675629836155808, 0.8710144010779794 ] }, "II": { "k": 171, "n": 200, "p": 0.855, "ci95": [ 0.7995134505428394, 0.8971064211069184 ] }, "III": { "k": 171, "n": 198, "p": 0.8636363636363636, "ci95": [ 0.8088693626231386, 0.9045619214376489 ] } }, "other_issues": { "k": 153, "n": 200, "p": 0.765, "ci95": [ 0.7015864484736013, 0.8184255683917109 ] }, "answer_status": { "k": 144, "n": 200, "p": 0.72, "ci95": [ 0.6540770944519325, 0.7776309950211568 ] }, "gold_tier_criterion_acc": { "r1-3/3": { "k": 467, "n": 521, "p": 0.8963531669865643, "ci95": [ 0.8672147027925656, 0.9196896191692199 ] }, "r2-3/3": { "k": 13, "n": 23, "p": 0.5652173913043478, "ci95": [ 0.36811411127539473, 0.7436533513557193 ] }, "r2-2/3": { "k": 26, "n": 51, "p": 0.5098039215686274, "ci95": [ 0.37680949168569783, 0.6414248935095266 ] }, "human": { "k": 6, "n": 9, "p": 0.6666666666666666, "ci95": [ 0.35420266530928485, 0.8794159360350102 ] } }, "other_issues_split": { "has_error_recall": { "k": 42, "n": 53, "p": 0.7924528301886793, "ci95": [ 0.6654228381471919, 0.8799538844327056 ] }, "no_error_specificity": { "k": 111, "n": 147, "p": 0.7551020408163265, "ci95": [ 0.6796736041927686, 0.8175372312920278 ] } }, "confusion": { "contradicted->(없음)": 1, "contradicted->contradicted": 124, "contradicted->missing": 5, "contradicted->supported": 2, "contradicted->unclear": 1, "missing->contradicted": 7, "missing->missing": 102, "missing->supported": 22, "missing->unclear": 11, "supported->contradicted": 6, "supported->missing": 9, "supported->supported": 263, "supported->unclear": 5, "unclear->(없음)": 2, "unclear->contradicted": 6, "unclear->missing": 3, "unclear->supported": 12, "unclear->unclear": 23 } }, "base": { "key": "qwen9b", "label": "Qwen3.5-9B (base)", "hf": "Qwen/Qwen3.5-9B", "serving": "RunPod A40 Pod, vLLM 0.32.0, bf16", "name": "Qwen3.5-9B (기본)", "answers": 200, "missing_output": 0, "json_invalid": 0, "criterion_acc": { "mean": 0.76625, "ci95": [ 0.7304187083476741, 0.8020812916523259 ], "n_answers": 200 }, "criterion_acc_excl_r2_2of3": { "mean": 0.81375, "ci95": [ 0.7792670360036391, 0.8482329639963608 ], "n_answers": 200 }, "criterion_micro": { "hit": 463, "n": 604 }, "misconception": { "k": 86, "n": 133, "p": 0.6466165413533834, "ci95": [ 0.5623037851806594, 0.7226975936965256 ] }, "misconception_with_id": { "k": 62, "n": 79, "p": 0.7848101265822784, "ci95": [ 0.6821285476156216, 0.8610778266442956 ] }, "json_valid": { "k": 200, "n": 200, "p": 1.0, "ci95": [ 0.981154748802476, 1.0 ] }, "unit_criterion_micro": { "I": { "k": 152, "n": 206, "p": 0.7378640776699029, "ci95": [ 0.6738455884077236, 0.793173692935328 ] }, "II": { "k": 156, "n": 200, "p": 0.78, "ci95": [ 0.7176121367571497, 0.8318345225722368 ] }, "III": { "k": 155, "n": 198, "p": 0.7828282828282829, "ci95": [ 0.7203091094117178, 0.8345818893022281 ] } }, "other_issues": { "k": 153, "n": 200, "p": 0.765, "ci95": [ 0.7015864484736013, 0.8184255683917109 ] }, "answer_status": { "k": 96, "n": 200, "p": 0.48, "ci95": [ 0.41179179908760966, 0.5489620109602914 ] }, "gold_tier_criterion_acc": { "r1-3/3": { "k": 440, "n": 521, "p": 0.8445297504798465, "ci95": [ 0.810905474589728, 0.8731106309412187 ] }, "r2-3/3": { "k": 7, "n": 23, "p": 0.30434782608695654, "ci95": [ 0.15604046185489862, 0.5086571502517591 ] }, "r2-2/3": { "k": 13, "n": 51, "p": 0.2549019607843137, "ci95": [ 0.15545784189248602, 0.38868252822690164 ] }, "human": { "k": 3, "n": 9, "p": 0.3333333333333333, "ci95": [ 0.12058406396498972, 0.6457973346907151 ] } }, "other_issues_split": { "has_error_recall": { "k": 7, "n": 53, "p": 0.1320754716981132, "ci95": [ 0.06547862476439556, 0.24840227263508838 ] }, "no_error_specificity": { "k": 146, "n": 147, "p": 0.9931972789115646, "ci95": [ 0.9624761437110765, 0.9987981382261968 ] } }, "confusion": { "contradicted->contradicted": 113, "contradicted->missing": 9, "contradicted->supported": 9, "contradicted->unclear": 2, "missing->contradicted": 13, "missing->missing": 72, "missing->supported": 47, "missing->unclear": 10, "supported->contradicted": 5, "supported->missing": 2, "supported->supported": 270, "supported->unclear": 6, "unclear->contradicted": 7, "unclear->missing": 3, "unclear->supported": 28, "unclear->unclear": 8 } }, "paired_ft_minus_base": { "all": { "diff": 0.0825, "ci95": [ 0.04932451957550776, 0.11567548042449224 ], "n": 200, "verdict": "개선" }, "no_majority": { "diff": 0.06333333333333334, "ci95": [ 0.02673315576101877, 0.09993351090564791 ], "n": 200, "verdict": "개선" } } }