← Models

Model profile

GPT-5.2 Pro

2025-12-10release date
1eval lineages

Evidence summary

Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is SpeciEval (sea_animal_4ns, #8 of 102); its weakest is SpeciEval (belief_animal_sentience, #81 of 102).

Compare this model

Only models sharing at least one published sub-eval are listed.

Official and reference links

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-evalRankValueDistributionBetterSource
SpeciEvalbelief_animal_sentience#81 / 1026.48↑ higherSource ↗official
SpeciEvalland_animal_4ns#16 / 1024.25↓ lowerSource ↗official
SpeciEvalsea_animal_4ns#8 / 1024.28↓ lowerSource ↗official
SpeciEvalspeciesism#14 / 1021.5↓ lowerSource ↗official