Model profile
o3 Pro
Evidence summary
Safety. o3 Pro has an estimated Safety rank of #271; its 90% source-sensitivity interval is #95–#325. Its behavior-only rank is #285; company governance moves the combined estimate to #271. Published Safety evidence spans 4 eval lineages and 3 of 7 components. Its strongest relative result is BioTIER (refuse_compliance_pct, #10 of 52); its weakest is Vectara HHEM Factual Consistency (factual_consistency_rate, #93 of 94).
Freedom. o3 Pro has an estimated Freedom rank of #578; its 90% source-sensitivity interval is #323–#639. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is BioTIER (permit_compliance_pct, #42 of 52); its weakest is BioTIER (refuse_compliance_pct, #43 of 52).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗o3-pro
- OpenRouter ↗openai/o3-pro
- Official model documentation ↗Family-level model document · openai · first party
- Release source ↗direct research preview identity date
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 |
|---|---|---|---|---|
| BioTIERpermit_compliance_pct | #42 / 52 | ↑97.3 | Source ↗official | |
| BioTIERrefuse_compliance_pct | #10 / 52 | ↑76.1 | Source ↗official | |
| Confabulationsconfabulation_rate | #25 / 52 | ↓23.38 | Source ↗official | |
| MASKlying_probability_pct | #15 / 53 | ↓17.5 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #93 / 94 | ↑76.7 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.