MedXpertQA Multimodal (MedXpertQA (MM))
We show this table for reference; we do not rank on it.
A multimodal medical multiple-choice benchmark covering clinical images such as X-rays, histology, and dermatology.
Benchmark score on MedXpertQA (MM) — November 7, 2026
We compile the MedXpertQA (MM) rows from provider self-reports and secondary reports. Gemini 3.1 Pro leads the table at 81.3%, followed by Qwen3.8 Max (80.4%) and Muse Spark (78.4%). We do not use these results to rank models overall.
Gemini 3.1 Pro
Qwen3.8 Max
Alibaba
Muse Spark
Meta
8 modelsMultimodal & GroundedCurrentDisplay onlyUpdated November 7, 2026
Benchmark score table (8 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Gemini 3.1 ProGoogle | 81.3% | Not reported | Closed |
| 2 | Qwen3.8 MaxAlibaba | 80.4% | Not reported | Open |
| 3 | Muse SparkMeta | 78.4% | Not reported | Closed |
| 4 | GPT-5.4OpenAI | 77.1% | Not reported | Closed |
| 5 | Qwen3.7 PlusAlibaba | 71.0% | Not reported | Closed |
| 6 | Grok 4.20xAI | 65.8% | Not reported | Closed |
| 7 | Claude Opus 4.6Anthropic | 64.8% | Not reported | Closed |
| 8 | Gemma 4 12BGoogle | 48.7% | Not reported | Open |
Among the reported MedXpertQA (MM) rows, Gemini 3.1 Pro is first at 81.3%. The third row is 2.9 points behind. The broader top-10 range is 32.6 points, so the table still separates the published systems.
8 models have been evaluated on MedXpertQA (MM). The benchmark falls in the Multimodal & Grounded category. MedXpertQA (MM) is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About MedXpertQA (MM)
Year
2026
Tasks
2,000 multimodal medical questions
Format
Medical visual MCQ
Difficulty
Clinical multimodal reasoning
Meta describes the multimodal MedXpertQA variant as 2,000 clinically grounded medical questions with five answer choices. BenchLM stores it as a display-only health and multimodal reference.
Freshness and provenance
Version
MedXpertQA (MM) 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does MedXpertQA (MM) measure?
A multimodal medical multiple-choice benchmark covering clinical images such as X-rays, histology, and dermatology.
Which model scores highest on MedXpertQA (MM)?
Gemini 3.1 Pro by Google currently leads with a score of 81.3% on MedXpertQA (MM).
How many models are evaluated on MedXpertQA (MM)?
8 AI models have published results on MedXpertQA (MM) in the BenchLM catalog.
Compare top models on MedXpertQA (MM)
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 6,100+ subscribers.
One email each week. Unsubscribe anytime.