Claude 3.7 Sonnet
Anthropic
rich detail 27 method fields published
Evaluation
Biological risk evaluations (Claude 3.7 Sonnet)
human uplift studies on long-form end-to-end tasks; expert red-teaming (bacterial and virology scenarios); multiple-choice knowledge/skill evaluations; open-ended pathway-step questions; task-based agentic evaluations with search and bioinformatics tools
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.