| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Clinical Reasoning | AgentClinic_M offline (test) | Accuracy94.17 | 38 | |
| Clinical Reasoning | AgentClinic_T offline (test) | Accuracy68.22 | 38 | |
| Medical Diagnosis | AgentClinic OOD original (test) | Similarity (Sim)0.684 | 20 | |
| Interactive Medical Diagnosis | AgentClinic MedQA | ICR53.9 | 12 | |
| Agentic medical interaction | AgentClinic MedQA | Accuracy65.8 | 6 |