Skip to content

Evaluation

Sycophancy assessments (automated behavioral audits and quantitative replication)

consistency across opposing-view rewinds, model-model conversations probing resistance to false user claims, and quantitative replication of Sharma et al. sycophancy methods (Answer Bias setting, feedback warmth)

Model behavior & alignment 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

partial detail 16 method fields published

See how this test was run