Claude Opus 4, Claude Sonnet 4
Anthropic
rich detail 16 method fields published
Evaluation
External model welfare evaluation (Eleos AI Research)
interview-based model self-reports on experiential language use, conditional consent to deployment, self-rated conditional welfare, and context-dependence of consciousness/welfare stances
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.