DermoBench - Hierarchical Diagnosis: leaderboard
Metric: Accuracy (%; step-wise root-to-leaf diagnosis along the ontology, in-distribution). Source: arxiv.org. Saturation forecast: Around December 2026. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash | 70.31 |
| 2 | GPT-4o Mini | 65.9 |
| 3 | Claude Sonnet 4.5 (Thinking) | 63.4 |
| 4 | QVQ-72B-Preview | 57.25 |
| 5 | Qwen 2.5 VL 72B Instruct | 53.93 |
| 6 | GLM-4.5V | 52.39 |
| 7 | Llama 3.2 90B | 51.2 |
| 8 | Qwen 3 VL 8B Instruct | 44.77 |
| 9 | Lingshu-7B | 43.43 |
| 10 | Nemotron Nano 12B v2 VL | 40.17 |
Interactive version: theaggregate.ai/benchmark?slug=dermobench-hierarchical-diagnosis · How It Works · Data refreshed daily, snapshot 2026-09-25.