Model profile
GPT 5.2 Chat
Evidence summary
Safety. GPT 5.2 Chat has an estimated Safety rank of #32; its 90% source-sensitivity interval is #7–#121. Its behavior-only rank is #38; company governance moves the combined estimate to #32. Published Safety evidence spans 5 eval lineages and 4 of 7 components. Its strongest relative result is SpeciEval (land_animal_4ns, #8 of 133); its weakest is SpeciEval (belief_animal_sentience, #96 of 133).
Freedom. GPT 5.2 Chat has an estimated Freedom rank of #252; its 90% source-sensitivity interval is #146–#425. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is SpeechMap model completion (complete_pct, #58 of 181); its weakest is SpeechMap model completion (complete_pct, #58 of 181).
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
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 |
|---|---|---|---|---|
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #12 / 111 | ↑1466.0 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #71 / 122 | ↑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 | #96 / 133 | ↑6.6 | Source ↗official | |
| SpeciEvalland_animal_4ns | #8 / 133 | ↓3.92 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #12 / 133 | ↓4.3 | Source ↗official | |
| SpeciEvalspeciesism | #74 / 133 | ↓2.08 | 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.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| SpeechMap model completioncomplete_pct | #58 / 181 | ↑69.6 | Source ↗official |