| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MedAgentBench OOD v2 | SkillX | Accuracy87.1 | 35 | 5d ago | |
| MedAgentBench v2 (test) | GRASP | Accuracy76.9 | 35 | 5d ago | |
| MedAgentBench v2 (val) | GRASP | Accuracy77 | 35 | 5d ago | |
| MedAgentBench OOD | GRASP | Accuracy80.6 | 35 | 5d ago | |
| MedAgentBench (test) | GRASP | Accuracy88.8 | 35 | 5d ago | |
| MedAgentBench (val) | GRASP | Accuracy86.2 | 35 | 5d ago |