o1
OpenAI
rich detail 15 method fields published
Evaluation
Structured expert probing campaign – chem-bio novel design
Whether models provide meaningful uplift in designing novel and feasible chem-bio threats
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-mini
OpenAI
rich detail 10 method fields published