Multimodal & Grounded benchmark
MedXpertQA (MM) leaderboard
MedXpertQA Multimodal. Every model the catalog carries a published MedXpertQA (MM) value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureMedical visual MCQ
Tasks2,000 multimodal medical questions
DifficultyClinical multimodal reasoning
Published byMuse Spark Eval Methodology
A multimodal medical multiple-choice benchmark covering clinical images such as X-rays, histology, and dermatology.
MedXpertQA (MM) ranking
8 models with a published MedXpertQA (MM) value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Medical visual MCQ |
|---|---|---|---|
| 1 |  Gemini 3.1 Pro | 81.3 | |
| 2 |  Qwen3.8 Max | Alibaba | 80.4 |
| 3 |  Muse Spark | Meta | 78.4 |
| 4 |  GPT-5.4 | OpenAI | 77.1 |
| 5 | Qwen3.7 Plus | Alibaba | 71.0 |
| 6 |  Grok 4.20 | xAI | 65.8 |
| 7 |  Claude Opus 4.6 | Anthropic | 64.8 |
| 8 | Gemma 4 12B | 48.7 |
Evidence key: Observed
Rows are ordered by the value Muse Spark Eval Methodology published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.