Multimodal · Benchmark profile
A multimodal medical multiple-choice benchmark covering clinical images such as X-rays, histology, and dermatology.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on MedXpertQA Multimodal
Gemini 3.1 Pro leads at 81.3%, followed by Muse Spark (78.4%) and GPT-5.4 (77.1%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
7 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Gemini 3.1 Pro | #1 | 81.3% | |
| Muse Spark | #2 | Meta | 78.4% |
| GPT-5.4 | #3 | OpenAI | 77.1% |
| Qwen3.7-Plus | #4 | Alibaba Cloud | 71% |
| Grok 4.20 | #5 | xAI | 65.8% |
| Claude Opus 4.6 | #6 | Anthropic | 64.8% |
| Gemma 4 12B | #7 | 48.7% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Gemini 3.1 Pro gemini-3-1-pro | closed | Estimated reference | 81.3% | |
| #2 | Muse Spark muse-spark | Meta | closed | Reference only | 78.4% |
| #3 | GPT-5.4 gpt-5.4 | OpenAI | closed | Reference only | 77.1% |
| #4 | Qwen3.7-Plus qwen3.7-plus | Alibaba Cloud | — | Reference only | 71% |
| #5 | Grok 4.20 grok-4.20 | xAI | closed | Estimated reference | 65.8% |
| #6 | Claude Opus 4.6 claude-opus-4-6 | Anthropic | closed | Reference only | 64.8% |
| #7 | Gemma 4 12B gemma-4-12b | open | Estimated reference | 48.7% |
The top of this snapshot is led by Gemini 3.1 Pro at 81.3%; third place is 4.2 points behind. The top-7 spread is 32.6 points.
About MedXpertQA Multimodal
A multimodal medical multiple-choice benchmark covering clinical images such as X-rays, histology, and dermatology. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
A multimodal medical multiple-choice benchmark covering clinical images such as X-rays, histology, and dermatology.
Gemini 3.1 Pro by Google currently leads with 81.3%.
7 models in the LuminaBench cohort have a qualifying score on this benchmark.
Related
