multimodal benchmark
MedXpertQA
A comprehensive benchmark to evaluate expert-level medical knowledge and advanced reasoning, featuring 4,460 questions spanning 17 specialties and 11 body systems. Includes both text-only and multimodal subsets with expert-level exam questions incorporating diverse medical images and rich clinical information.
Updated Aug 11, 2026
Models12
Model coverage12
MetricScore
EvidenceB
MedXpertQA Ranking
Higher score ranks better on this benchmark.
| 01 | ME | 78.4% | 100.0% | 12 | C | |
| 02 | AC | 67.3% | 90.9% | 12 | C | |
| 03 | AC | 62.4% | 81.8% | 12 | C | |
| 04 | AC | 61.4% | 72.7% | 12 | C | |
| 05 | GO | 61.3% | 63.6% | 12 | C | |
| 06 | GO | 58.1% | 54.5% | 12 | C | |
| 07 | GO | 49.0% | 45.5% | 12 | C | |
| 08 | GO | 48.7% | 36.4% | 12 | C | |
| 09 | MI | 43.0% | 27.3% | 12 | C | |
| 10 | GO | 28.7% | 18.2% | 12 | C | |
| 11 | GO | 23.5% | 9.1% | 12 | C | |
| 12 | GO | 18.8% | 0.0% | 12 | C |
MedXpertQA Score Distribution
A closer view of the leading scores on this benchmark.
MedXpertQA Highlights
The leading models and scores on this benchmark.
What is MedXpertQA?
What MedXpertQA measures and how its scores work.
A comprehensive benchmark to evaluate expert-level medical knowledge and advanced reasoning, featuring 4,460 questions spanning 17 specialties and 11 body systems. Includes both text-only and multimodal subsets with expert-level exam questions incorporating diverse medical images and rich clinical information.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MedXpertQA
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- medxpertqa|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MedXpertQA.
Which model scores highest on MedXpertQA?
Muse Spark is currently ranked first with 78.4%.
What does MedXpertQA measure?
A comprehensive benchmark to evaluate expert-level medical knowledge and advanced reasoning, featuring 4,460 questions spanning 17 specialties and 11 body systems. Includes both text-only and multimodal subsets with expert-level exam questions incorporating diverse medical images and rich clinical information.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
12 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.