| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MMedbench English subset (val) | LLaMA3-8B | Accuracy60.33 | 36 | 1mo ago | |
| Medical Knowledge Item Bank CAT | Test Length73 | 22 | 23d ago | ||
| Medical Knowledge Item Bank Full 2815 items | Theta2.25 | 22 | 23d ago | ||
| MMLU Med | Gemini 3 Pro | Accuracy88.1 | 11 | 10d ago | |
| CMMLU Med | Accuracy86.89 | 5 | 1mo ago | ||
| CEVAL Med | Accuracy91.46 | 5 | 1mo ago | ||
| MedQA-USMLE | DOS-CPT | Accuracy73.61 | 5 | 1mo ago | |
| NEJMQA | DOS-CPT | Accuracy66.14 | 5 | 1mo ago | |
| Medbullets | Accuracy58.44 | 5 | 1mo ago | ||
| GPQA Med | DOS-CPT | Accuracy63.16 | 5 | 1mo ago | |
| DiagnosisArena | DOS-CPT | Accuracy61.11 | 5 | 1mo ago |