| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| AgentClinic_T offline (test) | SkeMex | Accuracy68.22 | 38 | 1mo ago | |
| ER-Reason | Kimi-2.6 | Accuracy34.4 | 26 | 1mo ago | |
| MIMIC-CDM-FI | DeepSeek-V4 | Accuracy90.1 | 26 | 1mo ago | |
| MedCaseReasoning | GPT-5.0 | Accuracy54.96 | 26 | 1mo ago | |
| MedR-Bench Treatment | GSEM | Accuracy94.59 | 18 | 4mo ago | |
| MedR-Bench Diagnosis | GSEM | Accuracy94.22 | 18 | 4mo ago | |
| MEDREASON | Outcome Reward | Pass@173.4 | 15 | 3mo ago | |
| HealthBench Professional (525 cases) | MDIA v1.0.53 | Overall Score62.72 | 11 | 2mo ago | |
| Expert-ECG-QA | CARE-ECG | Accuracy84 | 8 | 3mo ago | |
| CoEval custom Clinical reasoning vertical | CoEval Ensemble Score87.3 | 3 | 1mo ago |