| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MIMIC-IV (test) | Meissa | Accuracy84.4 | 6 | 1mo ago | |
| MedQA Extension (test) | Gemini-3-flash | Accuracy92.3 | 6 | 1mo ago | |
| NEJM Extension OOD (test) | Gemini-3-flash | Accuracy33.3 | 6 | 1mo ago | |
| NEJM OOD (test) | Meissa | Accuracy46.7 | 6 | 1mo ago |