Skip to content

Anthropic biomedical-image-analysis evaluation

Quantitative biomedical image analysis across segmentation, detection, measurement, classification, registration, reconstruction, and tracking tasks.

2 models

Higher is better.

  1. 1Claude Sonnet 5.5Anthropic72.2
  2. 2Claude Opus 5.5Anthropic71.4
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Normalized task metric
Tasks
91 cases across 31 biomedical imaging tasks
Authors
Anthropic (2026)

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