| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Medical Domain (MedQA, MMLU, MedMCQA) (test) | GPT-4.1 (25-04-14) | MedQA Score92.5 | 45 | 4d ago | |
| MMLU Clinical Knowledge | GPT-4o | Accuracy92 | 10 | 4d ago | |
| MMLU College Medicine | GPT-4o | Accuracy89 | 4 | 4d ago | |
| MMLU College Biology | GPT-4o | Accuracy95 | 4 | 4d ago | |
| MMLU Anatomy | GPT-4o | Accuracy89 | 4 | 4d ago | |
| MMLU Medical Genetics | GPT-4o | Accuracy96 | 4 | 4d ago |