Claude 3.7 Sonnet
Anthropic
rich detail 19 method fields published
Evaluation
Harms and faithfulness in extended thinking mode
harm potential across three parts of a completion (thinking block, final output, CoT outside official blocks); tested with jailbreak techniques (chain-of-thought elicitation, gradualism, reframing)
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.