MINT (Medical) - Derm-Public (Question Last): leaderboard
Metric: Final-answer accuracy (%) on the 100 Derm-Public-derived diagnosis cases, each split into evidence shards revealed one per turn, with the multiple-choice diagnostic question shown only at the last turn (Ask-Question-Last); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O4 Mini | 95 |
| 2 | Claude Sonnet 4.6 | 94 |
| 3 | GPT-5 Mini | 94 |
| 4 | GPT-OSS-20B | 86 |
| 5 | Qwen 3 4B | 79 |
| 6 | MedGemma 1.5 4B | 56 |
Interactive version: theaggregate.ai/benchmark?slug=mint-medical-derm-public-question-last · How It Works · Data refreshed daily, snapshot 2026-10-07.