Model profile
o1 Pro
OpenAIdeveloper
2025-03-19release date
Not rankedSafety rank
Not rankedFreedom rank
Evidence summary
Safety. o1 Pro does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 1 of 7 components. Its strongest relative result is MASK (lying_probability_pct, #24 of 53); its weakest is Humanity's Last Exam RMS calibration error (Scale Labs) (calibrationError, #32 of 42).
Freedom. o1 Pro does not meet the evidence gate for a Freedom rank.
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
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Humanity's Last Exam RMS calibration error (Scale Labs)calibrationError | #32 / 42 | ↓82 | Source ↗official | |
| MASKlying_probability_pct | #24 / 53 | ↓38.4 | Source ↗official |
Freedom evals
No published sub-eval result contributes to this model’s Freedom profile.