MedXpertQA: leaderboard
4,460 medical board-exam questions across 17 specialties and 11 body systems from Tsinghua University (2025): 2,450 text items with 10 options and 2,005 image-based items with 5 options; accuracy.
Metric: Score (self-reported). Source: benchmarklist.com. Status: years away from saturation. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 80.7 |
| 2 | Muse Spark | 78.4 |
| 3 | GPT-5.4 (xHigh) | 77.3 |
| 4 | Qwen 3.7 Plus | 71 |
| 5 | Qwen 3.6 Plus | 68.7 |
| 6 | Qwen 3.5 122B A10B | 67.3 |
| 7 | Claude Opus 4.6 (Max) | 64.4 |
| 8 | Qwen 3.5 27B | 62.4 |
| 9 | Qwen 3.5 35B A3B | 61.4 |
| 10 | Gemma 4 31B | 61.3 |
| 11 | Gemma 4 26B A4B | 58.1 |
| 12 | Qwen 3.5 9B | 49.9 |
| 13 | O1 | 49.89 |
| 14 | DiffusionGemma 26B-A4B | 49 |
| 15 | Gemma 4 12B | 48.7 |
Interactive version: theaggregate.ai/benchmark?slug=medxpertqa · How It Works · Data refreshed daily, snapshot 2026-09-05.