Benchmark
MedXpertQA Benchmark
What is MedXpertQA?
A comprehensive benchmark to evaluate expert-level medical knowledge and advanced reasoning, featuring 4,460 questions spanning 17 specialties and 11 body…
- Modality
- multimodal
- Evaluates
- multimodal, reasoning, healthcare, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 12
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/medxpertqa?top_n=500
MedXpertQA results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| DiffusionGemma 26B-A4B | 0.49 | 2026-06-10 | evidence | |
| Gemma 4 12B | 0.487 | 2026-05-23 | evidence | |
| Gemma 4 26B-A4B | 0.581 | 2026-04-02 | evidence | |
| Gemma 4 31B | 0.613 | 2026-04-02 | evidence | |
| Gemma 4 E2B | 0.235 | 2026-04-02 | evidence | |
| Gemma 4 E4B | 0.287 | 2026-04-02 | evidence | |
| MAI-Thinking-1 | Microsoft | 0.43 | 2026-06-02 | evidence |
| MedGemma 4B IT | 0.188 | 2025-05-20 | evidence | |
| Muse Spark | Meta | 0.784 | 2026-04-08 | evidence |
| Qwen3.5-122B-A10B | Qwen | 0.673 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.624 | 2026-02-24 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.614 | 2026-02-24 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.