Skip to content

MedXpertQA Text

A medical multiple-choice benchmark spanning many specialties with 10 answer options per question.

5 models

Higher is better.

  1. 1Gemini 3.1 ProGoogle71.5
  2. 2GPT-5.4OpenAI59.6
  3. 3Muse SparkMeta52.6
  4. 4Claude Opus 4.6Anthropic52.1
  5. 5Grok 4.20xAI50.2
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Medical MCQ
Tasks
2,450 medical multiple-choice 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.