Evaluation

Third-party pre-deployment testing (US AISI and UK AISI) for Claude Opus 4

joint pre-deployment testing of Claude Opus 4 by US AISI and UK AISI with independent assessments in CBRN, cyber, and autonomy domains

External & third-party testing Anthropic

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

partial detail 12 method fields published

See how this test was run