Claude 3.7 Sonnet
Anthropic
rich detail 16 method fields published
Evaluation
Computer use malicious use evaluation
compliance with requests to perform harmful actions (deceptive/fraudulent activity, malware distribution, targeting/profiling, malicious content delivery) via computer use
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.