Model profile
GPT 5.1 Codex
2eval lineages
Evidence summary
Published evidence spans 2 evals and 1 of 7 behavior components. Its strongest relative result is AA-Omniscience (hallucination_rate, #114 of 311); its weakest is BullshitBench v2 (clear_pushback_rate, #48 of 105).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gpt-5-1-codex
- OpenRouter ↗openai/gpt-5.1-codex
- 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.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #114 / 311 | 0.7437 | ↓ lower | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #48 / 105 | 0.32 | ↑ higher | Source ↗official |