Medmarks - MedQA — leaderboard
Metric: Score (%). Source: medmarks.ai. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 95.39 |
| 2 | GLM-4.7 FP8 | 94.79 |
| 3 | Grok 4 | 93.48 |
| 4 | GPT-OSS-120B (High) | 93.27 |
| 5 | Qwen 3 235B A22B (Thinking) | 92.96 |
| 6 | Claude Sonnet 4.5 | 92.83 |
| 7 | GPT-OSS-120B (Medium) | 91.54 |
| 8 | Qwen 3 Next 80B A3B (Thinking) | 91.12 |
| 9 | MiniMax-M2.1 | 91.1 |
| 10 | MiniMax-M2 | 90.7 |
| 11 | INTELLECT-3 | 90.52 |
| 12 | GPT-5.2 (Medium) | 90.49 |
| 13 | Qwen 3 Next 80B A3B Instruct | 90.08 |
| 14 | GPT-5.1 (Medium) | 89.74 |
| 15 | Qwen 3 VL 30B A3B (Thinking) | 89.08 |
Interactive version: theaggregate.ai/benchmark?slug=medmarks-medqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.