Medical Reasoning on MMLU-Pro (Hindi Medical)
50.7AccuracyGPT-4o
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GPT-4o2026.05 | 50.7 | 10 | |
| HuatuoGPT-o1-8BParameters=8B2026.05 | 41.3 | 23.4 | |
| LLaMA3-8B-UltraMedicalParameters=8B, Backbone=LLaMA32026.05 | 34 | 27.3 |
| Method | Links | ||
|---|---|---|---|
| GPT-4o2026.05 | 50.7 | 10 | |
| HuatuoGPT-o1-8BParameters=8B2026.05 | 41.3 | 23.4 | |
| LLaMA3-8B-UltraMedicalParameters=8B, Backbone=LLaMA32026.05 | 34 | 27.3 |