| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| ReMeDi | APP-DeepSeek-v3 | Accuracy (Neurology)3.9 | 14 | 2mo ago | |
| PubMed VivaBench evaluation setup | MeDxAgent | Accuracy43.5 | 6 | 1mo ago | |
| MedQA 214 | MeDxAgent | Accuracy71.5 | 2 | 1mo ago | |
| MIMIC 288 | MeDxAgent | Accuracy76.04 | 2 | 1mo ago | |
| NEJM 120 | MeDxAgent | Accuracy41.67 | 2 | 1mo ago |