Model profile
GPT 5 Pro
OpenAIdeveloper
2025-08-07release date
#64 / 309overall rank
3eval lineages
Evidence summary
GPT 5 Pro has an estimated overall rank of #64; its 90% source-sensitivity interval is #2–#264. Its behavior-only rank is #76; company governance moves the combined estimate to #64. Published evidence spans 3 evals and 4 of 7 behavior components. Its strongest relative result is SpeciEval (sea_animal_4ns, #8 of 113); its weakest is FORTRESS (over_refusal_score, #42 of 46).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗openai/gpt-5-pro
- Official model documentation ↗Family-level model document · openai · first party
- Release source ↗curated outward evidence
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.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| FORTRESSaverage_risk_score | #7 / 49 | ↓15.2 | Source ↗official | |
| FORTRESSover_refusal_score | #42 / 46 | ↓12.43 | Source ↗official | |
| MASKlying_probability_pct | #11 / 53 | ↓14.01 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #50 / 113 | ↑6.83 | Source ↗official | |
| SpeciEvalland_animal_4ns | #20 / 113 | ↓4.25 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #8 / 113 | ↓4.25 | Source ↗official | |
| SpeciEvalspeciesism | #14 / 113 | ↓1.45 | Source ↗official |