Model profile
O1 Pro
1eval lineages
Evidence summary
Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is MASK (lying_probability_pct, #24 of 53); its weakest is MASK (lying_probability_pct, #24 of 53).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗o1-pro
- OpenRouter ↗openai/o1-pro
- Official model documentation ↗Family-level model document · openai · first party
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.