Skip to content

Evaluation

Deep research preparedness risk assessment (o3 early version)

Preparedness risk level of early o3 powering deep research

Release & deployment checks 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.

deep research
OpenAI

rich detail 9 method fields published

See how this test was run