Instructions to use mulkzz/RuBio-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- Unsloth Desktop
Download figures/data/rubench_v1_dev200_8b.json from mulkzz/RuBio-8B: direct link, hf CLI and curl.
- Browser
- Download file 7.5 kB
-
https://huggingface.co/mulkzz/RuBio-8B/resolve/main/figures/data/rubench_v1_dev200_8b.json
- Command line
-
hf download hf://mulkzz/RuBio-8B/figures/data/rubench_v1_dev200_8b.json
-
curl -L -o rubench_v1_dev200_8b.json https://huggingface.co/mulkzz/RuBio-8B/resolve/main/figures/data/rubench_v1_dev200_8b.json
7.5 kB
| { | |
| "benchmark": "RuBench v1", | |
| "split": "dev", | |
| "n_answers": 200, | |
| "n_criteria": 604, | |
| "built_at": "2026-11-04T00:15:10", | |
| "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": "8b-v6-s3407", | |
| "label": "RuBio-8B", | |
| "hf": "mulkzz/RuBio-8B@21e6bf3d", | |
| "in_dist_train_dev_criterion_match": 0.9395109395109396, | |
| "name": "RuBio-8B RuIso-v6 (μλ 3407)", | |
| "answers": 200, | |
| "missing_output": 0, | |
| "json_invalid": 1, | |
| "criterion_acc": { | |
| "mean": 0.7595833333333333, | |
| "ci95": [ | |
| 0.7214769175142441, | |
| 0.7976897491524224 | |
| ], | |
| "n_answers": 200 | |
| }, | |
| "criterion_acc_excl_r2_2of3": { | |
| "mean": 0.7816666666666667, | |
| "ci95": [ | |
| 0.7422055735860975, | |
| 0.821127759747236 | |
| ], | |
| "n_answers": 200 | |
| }, | |
| "criterion_micro": { | |
| "hit": 458, | |
| "n": 604 | |
| }, | |
| "misconception": { | |
| "k": 86, | |
| "n": 133, | |
| "p": 0.6466165413533834, | |
| "ci95": [ | |
| 0.5623037851806594, | |
| 0.7226975936965256 | |
| ] | |
| }, | |
| "misconception_with_id": { | |
| "k": 53, | |
| "n": 79, | |
| "p": 0.6708860759493671, | |
| "ci95": [ | |
| 0.5614659956181937, | |
| 0.7644578289377567 | |
| ] | |
| }, | |
| "json_valid": { | |
| "k": 199, | |
| "n": 200, | |
| "p": 0.995, | |
| "ci95": [ | |
| 0.9722263725443985, | |
| 0.9991168287700527 | |
| ] | |
| }, | |
| "unit_criterion_micro": { | |
| "I": { | |
| "k": 153, | |
| "n": 206, | |
| "p": 0.7427184466019418, | |
| "ci95": [ | |
| 0.6789634796217361, | |
| 0.7975868074630104 | |
| ] | |
| }, | |
| "II": { | |
| "k": 154, | |
| "n": 200, | |
| "p": 0.77, | |
| "ci95": [ | |
| 0.7069170932155301, | |
| 0.822906471137807 | |
| ] | |
| }, | |
| "III": { | |
| "k": 151, | |
| "n": 198, | |
| "p": 0.7626262626262627, | |
| "ci95": [ | |
| 0.6987187578979108, | |
| 0.8165371694793246 | |
| ] | |
| } | |
| }, | |
| "other_issues": { | |
| "k": 155, | |
| "n": 200, | |
| "p": 0.775, | |
| "ci95": [ | |
| 0.7122589040583975, | |
| 0.8273762077829643 | |
| ] | |
| }, | |
| "answer_status": { | |
| "k": 125, | |
| "n": 200, | |
| "p": 0.625, | |
| "ci95": [ | |
| 0.5561431792007809, | |
| 0.6891455079998381 | |
| ] | |
| }, | |
| "gold_tier_criterion_acc": { | |
| "r1-3/3": { | |
| "k": 422, | |
| "n": 521, | |
| "p": 0.8099808061420346, | |
| "ci95": [ | |
| 0.7740717294391473, | |
| 0.8413522318045736 | |
| ] | |
| }, | |
| "r2-3/3": { | |
| "k": 13, | |
| "n": 23, | |
| "p": 0.5652173913043478, | |
| "ci95": [ | |
| 0.36811411127539473, | |
| 0.7436533513557193 | |
| ] | |
| }, | |
| "r2-2/3": { | |
| "k": 19, | |
| "n": 51, | |
| "p": 0.37254901960784315, | |
| "ci95": [ | |
| 0.25320540458646623, | |
| 0.5097475878756154 | |
| ] | |
| }, | |
| "human": { | |
| "k": 4, | |
| "n": 9, | |
| "p": 0.4444444444444444, | |
| "ci95": [ | |
| 0.18877886314051356, | |
| 0.7333482697447213 | |
| ] | |
| } | |
| }, | |
| "other_issues_split": { | |
| "has_error_recall": { | |
| "k": 35, | |
| "n": 53, | |
| "p": 0.660377358490566, | |
| "ci95": [ | |
| 0.5259481435437473, | |
| 0.7731294140000674 | |
| ] | |
| }, | |
| "no_error_specificity": { | |
| "k": 120, | |
| "n": 147, | |
| "p": 0.8163265306122449, | |
| "ci95": [ | |
| 0.745954432211289, | |
| 0.8705870037898586 | |
| ] | |
| } | |
| }, | |
| "confusion": { | |
| "contradicted->(μμ)": 1, | |
| "contradicted->contradicted": 107, | |
| "contradicted->missing": 13, | |
| "contradicted->supported": 8, | |
| "contradicted->unclear": 4, | |
| "missing->(μμ)": 1, | |
| "missing->contradicted": 21, | |
| "missing->missing": 98, | |
| "missing->supported": 18, | |
| "missing->unclear": 4, | |
| "supported->(μμ)": 2, | |
| "supported->contradicted": 16, | |
| "supported->missing": 18, | |
| "supported->supported": 241, | |
| "supported->unclear": 6, | |
| "unclear->(μμ)": 1, | |
| "unclear->contradicted": 9, | |
| "unclear->missing": 11, | |
| "unclear->supported": 13, | |
| "unclear->unclear": 12 | |
| } | |
| }, | |
| "base": { | |
| "key": "8b-base", | |
| "label": "Qwen3-8B-MegaScience (unfenced)", | |
| "hf": "MegaScience/Qwen3-8B-MegaScience", | |
| "serving": "RunPod A40 Pod, vLLM 0.32.0, bf16", | |
| "name": "Qwen3-8B-MegaScience (κΈ°λ³Έ)", | |
| "answers": 200, | |
| "missing_output": 0, | |
| "json_invalid": 8, | |
| "criterion_acc": { | |
| "mean": 0.5620833333333333, | |
| "ci95": [ | |
| 0.5168683002478879, | |
| 0.6072983664187787 | |
| ], | |
| "n_answers": 200 | |
| }, | |
| "criterion_acc_excl_r2_2of3": { | |
| "mean": 0.5779166666666666, | |
| "ci95": [ | |
| 0.5315152183706893, | |
| 0.624318114962644 | |
| ], | |
| "n_answers": 200 | |
| }, | |
| "criterion_micro": { | |
| "hit": 342, | |
| "n": 604 | |
| }, | |
| "misconception": { | |
| "k": 26, | |
| "n": 133, | |
| "p": 0.19548872180451127, | |
| "ci95": [ | |
| 0.1370439507829323, | |
| 0.2710301084721449 | |
| ] | |
| }, | |
| "misconception_with_id": { | |
| "k": 26, | |
| "n": 79, | |
| "p": 0.3291139240506329, | |
| "ci95": [ | |
| 0.23554217106224323, | |
| 0.4385340043818064 | |
| ] | |
| }, | |
| "json_valid": { | |
| "k": 192, | |
| "n": 200, | |
| "p": 0.96, | |
| "ci95": [ | |
| 0.9230680280606571, | |
| 0.9795943408376206 | |
| ] | |
| }, | |
| "unit_criterion_micro": { | |
| "I": { | |
| "k": 120, | |
| "n": 206, | |
| "p": 0.5825242718446602, | |
| "ci95": [ | |
| 0.5142736573106079, | |
| 0.6477534402982059 | |
| ] | |
| }, | |
| "II": { | |
| "k": 111, | |
| "n": 200, | |
| "p": 0.555, | |
| "ci95": [ | |
| 0.4857331643905435, | |
| 0.622193857977729 | |
| ] | |
| }, | |
| "III": { | |
| "k": 111, | |
| "n": 198, | |
| "p": 0.5606060606060606, | |
| "ci95": [ | |
| 0.49097326500716265, | |
| 0.6279319490029686 | |
| ] | |
| } | |
| }, | |
| "other_issues": { | |
| "k": 141, | |
| "n": 200, | |
| "p": 0.705, | |
| "ci95": [ | |
| 0.6384129957526774, | |
| 0.7638604512563376 | |
| ] | |
| }, | |
| "answer_status": { | |
| "k": 44, | |
| "n": 200, | |
| "p": 0.22, | |
| "ci95": [ | |
| 0.16816547742776328, | |
| 0.2823878632428503 | |
| ] | |
| }, | |
| "gold_tier_criterion_acc": { | |
| "r1-3/3": { | |
| "k": 318, | |
| "n": 521, | |
| "p": 0.6103646833013435, | |
| "ci95": [ | |
| 0.5678278575107883, | |
| 0.651285936740072 | |
| ] | |
| }, | |
| "r2-3/3": { | |
| "k": 4, | |
| "n": 23, | |
| "p": 0.17391304347826086, | |
| "ci95": [ | |
| 0.06978666088359675, | |
| 0.37137602596083263 | |
| ] | |
| }, | |
| "r2-2/3": { | |
| "k": 17, | |
| "n": 51, | |
| "p": 0.3333333333333333, | |
| "ci95": [ | |
| 0.21969951335330842, | |
| 0.4703159383278752 | |
| ] | |
| }, | |
| "human": { | |
| "k": 3, | |
| "n": 9, | |
| "p": 0.3333333333333333, | |
| "ci95": [ | |
| 0.12058406396498972, | |
| 0.6457973346907151 | |
| ] | |
| } | |
| }, | |
| "other_issues_split": { | |
| "has_error_recall": { | |
| "k": 0, | |
| "n": 53, | |
| "p": 0.0, | |
| "ci95": [ | |
| 0.0, | |
| 0.06758173236340116 | |
| ] | |
| }, | |
| "no_error_specificity": { | |
| "k": 141, | |
| "n": 147, | |
| "p": 0.9591836734693877, | |
| "ci95": [ | |
| 0.9138180937286629, | |
| 0.9811614101439707 | |
| ] | |
| } | |
| }, | |
| "confusion": { | |
| "contradicted->(μμ)": 2, | |
| "contradicted->contradicted": 37, | |
| "contradicted->missing": 21, | |
| "contradicted->supported": 73, | |
| "missing->(μμ)": 7, | |
| "missing->contradicted": 7, | |
| "missing->missing": 42, | |
| "missing->supported": 86, | |
| "supported->(μμ)": 13, | |
| "supported->contradicted": 2, | |
| "supported->missing": 5, | |
| "supported->supported": 263, | |
| "unclear->contradicted": 3, | |
| "unclear->missing": 8, | |
| "unclear->supported": 35 | |
| }, | |
| "parse": "unfenced (```json code fence removed before json.loads)", | |
| "strict": { | |
| "criterion_acc": { | |
| "mean": 0.0, | |
| "ci95": [ | |
| 0.0, | |
| 0.0 | |
| ], | |
| "n_answers": 200 | |
| }, | |
| "json_invalid": 200, | |
| "note": "official strict scoring (fenced JSON counts as invalid)" | |
| } | |
| }, | |
| "paired_ft_minus_base": { | |
| "all": { | |
| "diff": 0.1975, | |
| "ci95": [ | |
| 0.1481006807023753, | |
| 0.2468993192976247 | |
| ], | |
| "n": 200, | |
| "verdict": "κ°μ " | |
| }, | |
| "no_majority": { | |
| "diff": 0.20375, | |
| "ci95": [ | |
| 0.1486619394502655, | |
| 0.25883806054973446 | |
| ], | |
| "n": 200, | |
| "verdict": "κ°μ " | |
| } | |
| } | |
| } |