Disease Diagnostic on Dermatology Disease Datasets (In-distribution)
0.6345BCN20k ScoreSkin-R1
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Skin-R1Model Type=Dermatology2025.11 | 0.6345 | 0.7214 | 0.6573 | 0.6608 | 0.4955 | 0.537 | 0.6385 | |
| InternVL3-8BModel Type=General2025.11 | 0.4996 | 0.4705 | 0.6009 | 0.3453 | 0.3364 | 0.5473 | 0.443 | |
| Qwen2.5-VL-7B-InstructModel Type=General2025.11 | 0.4911 | 0.5162 | 0.5033 | 0.3521 | 0.2962 | 0.4852 | 0.4367 | |
| HuatuoGPT-Vision-7BModel Type=Medical2025.11 | 0.4799 | 0.4944 | 0.4295 | 0.3638 | 0.2561 | 0.4719 | 0.4241 | |
| Qwen2.5-VL-32B-InstructModel Type=General2025.11 | 0.4746 | 0.4057 | 0.4469 | 0.3815 | 0.3596 | 0.5763 | 0.4307 | |
| MedGemma-4BModel Type=Medical2025.11 | 0.413 | 0.2627 | 0.3753 | 0.3767 | 0.2924 | 0.324 | 0.3548 | |
| LLaVA-v1.6-13BModel Type=General2025.11 | 0.3933 | 0.3779 | 0.4469 | 0.4121 | 0.3376 | 0.4193 | 0.396 | |
| Qwen3-VL-32B-InstructModel Type=General2025.11 | 0.3156 | 0.2363 | 0.3688 | 0.2801 | 0.2536 | 0.3304 | 0.2892 | |
| Qwen3-VL-8B-InstructModel Type=General2025.11 | 0.2947 | 0.2085 | 0.3275 | 0.2386 | 0.2354 | 0.2899 | 0.2585 | |
| LLaVA-Med-7bModel Type=Medical2025.11 | 0.2508 | 0.2091 | 0.2039 | 0.2503 | 0.2135 | 0.287 | 0.24 | |
| LLaVA-v1.6-7BModel Type=General2025.11 | 0.2299 | 0.2416 | 0.308 | 0.3046 | 0.2354 | 0.2885 | 0.2636 |