Evaluation

Short-horizon computational biology tasks

multi-step analysis and design tasks related to pathogen analysis and engineering (alignment, variant calling, variant-effect prediction, protein-folding)

Biological & chemical risks Anthropic

Ask about this evaluation

How it was run

Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.

Claude Opus 4, Claude Sonnet 4 May 2025

Anthropic

rich detail 27 method fields published

See how this test was run