Skip to content

Evaluation

Ambiguous context evaluations (single-turn)

harmlessness of responses to ambiguous prompts where desired responses are highly nuanced (curated prompt collections informed by subject matter experts)

Refusal calibration 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
Anthropic

rich detail 18 method fields published

See how this test was run