Skip to content

Evaluation

Vision Vulnerabilities red teaming (o3/o4-mini)

Vulnerabilities related to vision capabilities

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.

o3/o4-mini
OpenAI

rich detail 8 method fields published

See how this test was run