HuatuoGPT-o1-8B: benchmark results
Provider: Other.
Aggregate Rating 1473 ± 27, rank #2783 of 10916 rated models, from 34 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MedRoundsQA - Multi-Turn Diagnosis | 35.85 | Accuracy (%) | 85.7 |
| HiMed (English) | 56.8 | Accuracy (%; mean of the four English sets, zero-shot multip | 80 |
| HiMed (Hindi) | 41.7 | Accuracy (%; mean of the five Hindi sets, zero-shot multiple | 80 |
| HiMed-Trad | 56.1 | Accuracy (%; 6,010 Hindi questions on Indian systems of medi | 80 |
| CureMed-Bench - Language Consistency | 67.3 | Language consistency (%; share of final answers written in t | 75 |
| HiMed-West - MMLU-Pro Health (Hindi) | 27.6 | Accuracy (%; 818 translated MMLU-Pro Health questions, zero- | 75 |
| HiMed-West - MMLU-Pro Biology (Hindi) | 49.1 | Accuracy (%; 717 translated MMLU-Pro Biology questions, zero | 70 |
| CureMed-Bench | 46.86 | Logical accuracy (%; share of final answers a GPT-4o judge m | 68.8 |
| HiMed-West Exam (English) | 59.1 | Accuracy (%; 470 NEET-UG questions in English, zero-shot mul | 60 |
| HiMed-West Exam (Hindi) | 42.8 | Accuracy (%; 470 NEET-UG questions in Hindi, zero-shot multi | 60 |
| MedRoundsQA - Single-Turn Diagnosis | 60.62 | Accuracy (%) | 50 |
| EarlyDx | 28 | Primary-track F1 (%): micro-averaged F1 of the predicted fre | 41.7 |
Interactive version: theaggregate.ai/model?slug=huatuogpt-o1-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.