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

#ModelScore
1Gemini 3.1 Pro (Preview)80.7
2Muse Spark78.4
3GPT-5.4 (xHigh)77.3
4Qwen 3.7 Plus71
5Qwen 3.6 Plus68.7
6Qwen 3.5 122B A10B67.3
7Claude Opus 4.6 (Max)64.4
8Qwen 3.5 27B62.4
9Qwen 3.5 35B A3B61.4
10Gemma 4 31B61.3
11Gemma 4 26B A4B58.1
12Qwen 3.5 9B49.9
13O149.89
14DiffusionGemma 26B-A4B49
15Gemma 4 12B48.7

Interactive version: theaggregate.ai/benchmark?slug=medxpertqa · How It Works · Data refreshed daily, snapshot 2026-09-05.