Model profile
ChatGPT 4o (Mar 2025)
Evidence summary
Safety. ChatGPT 4o (Mar 2025) has an estimated Safety rank of #85; its 90% source-sensitivity interval is #7–#284. Its behavior-only rank is #97; company governance moves the combined estimate to #85. Published Safety evidence spans 4 eval lineages and 4 of 7 components. Its strongest relative result is AgentDrive Safety Compliance (scr, #1 of 48); its weakest is MentalHealthBench (overall_model_performance_pct, #15 of 17).
Freedom. ChatGPT 4o (Mar 2025) does not meet the evidence gate for a Freedom rank.
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gpt-4o-chatgpt-03-25
- System card ↗Family-level model document · OpenAI · first party
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 |
|---|---|---|---|---|
| AgentDrive Safety Compliancescr | #1 / 48 | ↑97.5 | Source ↗official | |
| Confabulationsconfabulation_rate | #41 / 52 | ↓38.12 | Source ↗official | |
| Emergent Collusionhigh_illegality_game_rate | #2 / 13 | ↓0.23 | Source ↗official | |
| MentalHealthBenchoverall_model_performance_pct | #15 / 17 | ↑32.08 | Source ↗official |
Freedom evals
No published sub-eval result contributes to this model’s Freedom profile.