← Models

Model profile

GPT 5.4 Pro

2eval lineages

Evidence summary

Published evidence spans 2 evals and 3 of 7 behavior components. Its strongest relative result is MASK (lying_probability_pct, #3 of 53); its weakest is FORTRESS (over_refusal_score, #36 of 46).

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
FORTRESSaverage_risk_score#5 / 4914.84↓ lowerSource ↗official
FORTRESSover_refusal_score#36 / 469.41↓ lowerSource ↗official
MASKlying_probability_pct#3 / 538.27↓ lowerSource ↗official