Evaluation

External scenario evaluations (Apollo Research) of early Claude Opus 4 snapshot

strategic deception rates, in-context scheming propensity, sandbagging, and sabotage capabilities assessed by Apollo Research on an early Claude Opus 4 snapshot

Model behavior & alignment 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 17 method fields published

See how this test was run