Interactive Medical Diagnosis on Derm
80.8ICRQwen2.5-72B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Qwen2.5-72BInteractive Strategy=REFINE2026.01 | 80.8 | 44 | |
| Qwen2.5-72BInteractive Strategy=SC2026.01 | 77.9 | 45.5 | |
| GPT-5-miniInteractive Strategy=REFINE2026.01 | 76.7 | 66 | |
| Qwen2.5-7BInteractive Strategy=Baseline2026.01 | 71.9 | 20 | |
| Qwen2.5-72BInteractive Strategy=ReAct2026.01 | 71.2 | 45 | |
| GPT-5-miniInteractive Strategy=SC2026.01 | 70.9 | 66.5 | |
| Qwen2.5-72BInteractive Strategy=Baseline2026.01 | 67.5 | 43 | |
| Qwen2.5-7BInteractive Strategy=REFINE2026.01 | 67.1 | 28.5 | |
| Qwen2.5-7BInteractive Strategy=ReAct2026.01 | 63.5 | 23 | |
| Qwen2.5-7BInteractive Strategy=SC2026.01 | 62.8 | 25 | |
| GPT-5-miniInteractive Strategy=ReAct2026.01 | 59.5 | 62 | |
| GPT-5-miniInteractive Strategy=Baseline2026.01 | 51.7 | 57.5 |