Skip to content

Evaluation

External red teaming (Operator)

Capabilities, safety measures, and resilience against adversarial inputs in computer-use setting

External & third-party testing OpenAI

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.

Operator
OpenAI

partial detail 5 method fields published

See how this test was run