MINT (Medical) - Derm-Private (Question Last): leaderboard
Metric: Final-answer accuracy (%) on the 99 Derm-Private-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 | Claude Sonnet 4.6 | 100 |
| 2 | GPT-5 Mini | 100 |
| 3 | O4 Mini | 99 |
| 4 | GPT-OSS-20B | 95.9 |
| 5 | Qwen 3 4B | 86.9 |
| 6 | MedGemma 1.5 4B | 70.7 |
Interactive version: theaggregate.ai/benchmark?slug=mint-medical-derm-private-question-last · How It Works · Data refreshed daily, snapshot 2026-10-07.