Skip to content

MedXpertQA Multimodal

A multimodal medical multiple-choice benchmark covering clinical images such as X-rays, histology, and dermatology.

8 models

Higher is better.

  1. 1Gemini 3.1 ProGoogle81.3
  2. 2Qwen3.8 MaxAlibaba80.4
  3. 3Muse SparkMeta78.4
  4. 4GPT-5.4OpenAI77.1
  5. 5Qwen3.7 PlusAlibaba71.0
  6. 6Grok 4.20xAI65.8
  7. 7Claude Opus 4.6Anthropic64.8
  8. 8Gemma 4 12BGoogle48.7
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Medical visual MCQ
Tasks
2,000 multimodal medical questions
Authors
Meta AI (2026)

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.