DermoBench - OOD Diagnosis - SNU134: leaderboard
Metric: Accuracy (%; 4-way MCQA in the source dataset's own label space, out-of-distribution). Source: arxiv.org. Saturation forecast: Around December 2026. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 68.75 |
| 2 | Qwen 2.5 VL 72B Instruct | 66.67 |
| 3 | Gemini 2.5 Flash | 65.42 |
| 4 | QVQ-72B-Preview | 62.92 |
| 5 | GPT-4o Mini | 59.17 |
| 6 | GLM-4.5V | 57.08 |
| 7 | Qwen 3 VL 8B Instruct | 55.42 |
| 8 | Nemotron Nano 12B v2 VL | 52.08 |
| 9 | Llama 3.2 90B | 49.58 |
| 10 | Lingshu-7B | 40 |
Interactive version: theaggregate.ai/benchmark?slug=dermobench-ood-diagnosis-snu134 · How It Works · Data refreshed daily, snapshot 2026-09-25.