| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MedCaseReasoning (test) | MultiDx | Reasoning Recall66.2 | 10 | 1mo ago | |
| ER-Reason | SEA (Qwen-8b) | Final Accuracy72.14 | 9 | 1mo ago | |
| DiReCT (test) | MultiDx | Reasoning Recall66.5 | 4 | 1mo ago | |
| NOVA | Gemini 2.0 Flash | Top-1 Accuracy24.2 | 3 | 5d ago |