Multi-turn Clinical Simulation on MIMIC-IV (test)
84.4AccuracyMeissa
Evaluation results
| Method | Links | |
|---|---|---|
| MeissaFramework=Framework IV, Inference Mode=Agent-based, Agent System=AgentClinic2026.03 | 84.4 | |
| Gemini-3-flashFramework=Framework IV, Inference Mode=Agent-based, Agent System=AgentClinic2026.03 | 70.6 | |
| Qwen3-VL-4BFramework=Framework IV, Inference Mode=Agent-based, Agent System=AgentClinic2026.03 | 61.1 | |
| Llama-3.3-70BFramework=Framework IV, Inference Mode=Agent-based, Agent System=AgentClinic2026.03 | 36.8 | |
| GPT-4oFramework=Framework IV, Inference Mode=Agent-based, Agent System=AgentClinic2026.03 | 34.4 | |
| Qwen2.5-72BFramework=Framework IV, Inference Mode=Agent-based, Agent System=AgentClinic2026.03 | 21.2 |