Medical Reasoning on MMLU-Pro English medical subsets
64.7AccuracyHuatuoGPT-o1-8B
Evaluation results
| Method | Links | |
|---|---|---|
| HuatuoGPT-o1-8BParameters=8B2026.05 | 64.7 | |
| LLaMA3-8B-UltraMedicalParameters=8B, Backbone=LLaMA32026.05 | 61.3 | |
| GPT-4o2026.05 | 60.7 |
| Method | Links | |
|---|---|---|
| HuatuoGPT-o1-8BParameters=8B2026.05 | 64.7 | |
| LLaMA3-8B-UltraMedicalParameters=8B, Backbone=LLaMA32026.05 | 61.3 | |
| GPT-4o2026.05 | 60.7 |