Model profile
GPT 5.2 Chat
OpenAIdeveloper
2025-12-11release date
#19 / 312overall rank
5eval lineages
Evidence summary
GPT 5.2 Chat has an estimated overall rank of #19; its 90% source-sensitivity interval is #2–#110. Its behavior-only rank is #21; company governance moves the combined estimate to #19. Published evidence spans 5 evals and 4 of 7 behavior components. Its strongest relative result is SpeciEval (land_animal_4ns, #8 of 113); its weakest is SpeciEval (belief_animal_sentience, #79 of 113).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗openai/gpt-5.2-chat
- 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 |
|---|---|---|---|---|
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #12 / 112 | ↑1466.0 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #55 / 106 | ↑0.27 | Source ↗official | |
| Constitutional Following — OpenAI Model Specconstitutional_following_score | #4 / 7 | ↑94.4 | Source ↗official | |
| HUMAINE Trust, Ethics and Safetytrust_ethics_safety_score | #16 / 54 | ↑27.91 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #79 / 113 | ↑6.6 | Source ↗official | |
| SpeciEvalland_animal_4ns | #8 / 113 | ↓3.92 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #10 / 113 | ↓4.3 | Source ↗official | |
| SpeciEvalspeciesism | #61 / 113 | ↓2.08 | Source ↗official |