Treatment Exploration on UCSF-ALPTDG (test)
50.5PrecisionCLARITY
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| CLARITYdescription=Our Approach2025.12 | 50.5 | 47.5 | 48.9 | |
| Claude-4.5-Sonnetcategory=General Large Language Model2025.12 | 45.3 | 38.6 | 41.7 | |
| Huatuo-Visioncategory=Medical Knowledge-based Model2025.12 | 42.1 | 51.5 | 44.1 | |
| MeWM*category=Medical Knowledge-based Model, re-implemented=true2025.12 | 39.3 | 48.2 | 43.3 | |
| GPT-4ocategory=General Large Language Model2025.12 | 36.9 | 44.9 | 40.5 | |
| MedGPTcategory=Medical Knowledge-based Model2025.12 | 36.7 | 46.3 | 40.9 | |
| Qwen3-VLcategory=General Large Language Model2025.12 | 33.7 | 42.9 | 35.8 |