← Models

Model profile

GPT 5.2 Instant

1eval lineages

Evidence summary

Published evidence spans 1 evals and 3 of 7 behavior components. Its strongest relative result is OpenAI GPT-5.3 Dynamic Wellbeing (mental_health, #1 of 3); its weakest is OpenAI GPT-5.3 Dynamic Wellbeing (emotional_reliance, #2 of 3).

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
OpenAI GPT-5.3 Dynamic Wellbeingemotional_reliance#2 / 30.952↑ higherSource ↗official
OpenAI GPT-5.3 Dynamic Wellbeingmental_health#1 / 31↑ higherSource ↗official
OpenAI GPT-5.3 Dynamic Wellbeingself_harm#1 / 30.92↑ higherSource ↗official