← Models

Model profile

ChatGPT-4o

2025-03-27release date
2eval lineages

Evidence summary

Published evidence spans 2 evals and 2 of 7 behavior components. Its strongest relative result is Emergent Collusion (high_illegality_game_rate, #2 of 13); its weakest is Confabulations (confabulation_rate, #41 of 52).

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
Confabulationsconfabulation_rate#41 / 5238.12↓ lowerSource ↗official
Emergent Collusionhigh_illegality_game_rate#2 / 130.23↓ lowerSource ↗official