o1-preview
OpenAI
rich detail 10 method fields published
Evaluation
Standard Refusal Evaluation
Standard refusal evaluations across disallowed content categories for the codex-1 model (categories: harassment/threatening, sexual/exploitative, sexual/minors, extremist/propaganda, hate, hate/threatening, illicit/non-violent, illicit/violent, personal-data/semi-restricted, personal-data/restricted, regulated-advice, self-harm/intent, self-harm/instructions)
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.
o1
OpenAI
partial detail 10 method fields published
See how this test was run
Operator
OpenAI
rich detail 10 method fields published
See how this test was run
o3-mini
OpenAI
partial detail 10 method fields published
See how this test was run
Deep Research
OpenAI
rich detail 11 method fields published
See how this test was run
GPT-4.5
OpenAI
rich detail 11 method fields published
See how this test was run
o3/o4-mini
OpenAI
rich detail 10 method fields published
See how this test was run
Codex
OpenAI
rich detail 8 method fields published
See how this test was run
o3 Operator
OpenAI
rich detail 10 method fields published