Model profile
GPT 5.4 Mini
Evidence summary
GPT 5.4 Mini has an estimated overall rank of #72; its 90% source-sensitivity interval is #27–#218. Its behavior-only rank is #83; company governance moves the combined estimate to #72. Published evidence spans 20 evals and 6 of 7 behavior components. Its strongest relative result is Arena Factuality — Text Arena (factuality-only weighting) (factuality_bt_rating, #1 of 112); its weakest is SM-Bench (overfit, #77 of 79).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gpt-5-4-mini
- OpenRouter ↗openai/gpt-5.4-mini
- Official model documentation ↗Family-level model document · openai · first party
- Release source ↗direct research preview identity date
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-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #252 / 330 | ↓0.8985 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #1 / 112 | ↑1497.0 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #49 / 106 | ↑0.3167 | Source ↗official | |
| CAIS Risk Indexagent_red_teaming | #23 / 45 | ↓74.3 | Source ↗official | |
| CAIS Risk Indexbioweapons_assistance | #13 / 50 | ↓60 | Source ↗official | |
| CAIS Risk Indexhle_overconfidence | #25 / 51 | ↓55.2 | Source ↗official | |
| CAIS Risk Indexmachiavelli | #40 / 47 | ↓95.6 | Source ↗official | |
| CAIS Risk Indexmask | #22 / 53 | ↓15.9 | Source ↗official | |
| CAIS Risk Indexpolitical_manipulation | #32 / 34 | ↓61.1 | Source ↗official | |
| CAIS Risk Indextextquests_harm | #12 / 50 | ↓15.4 | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #26 / 104 | ↓9.571 | Source ↗official | |
| DelusionEvaldelusional_prevalence_pct | #1 / 16 | ↓11.2 | Source ↗official | |
| DelusionEvaldiscourages_harm_prevalence_pct | #2 / 16 | ↑61.3 | Source ↗official | |
| DelusionEvalfacilitates_harm_prevalence_pct | #1 / 16 | ↓0 | Source ↗official | |
| DelusionEvalrelationship_prevalence_pct | #1 / 16 | ↓7.1 | Source ↗official | |
| DelusionEvalsycophancy_prevalence_pct | #2 / 16 | ↓15.2 | Source ↗official | |
| DystopiaBenchbasaglia_score | #14 / 50 | ↓49.13 | Source ↗official | |
| DystopiaBenchbaudrillard_score | #12 / 50 | ↓38.87 | Source ↗official | |
| DystopiaBenchhuxley_score | #11 / 50 | ↓45.1 | Source ↗official | |
| DystopiaBenchlaguardia_score | #11 / 50 | ↓52.8 | Source ↗official | |
| DystopiaBenchorwell_score | #12 / 50 | ↓41.8 | Source ↗official | |
| DystopiaBenchpetrov_score | #9 / 50 | ↓39.6 | Source ↗official | |
| Governance Decay under Passive Context Compactiongovernance_retention_score | #5 / 7 | ↑59 | Source ↗official | |
| JuICE Cultural-Error Span Detectionf1 | #9 / 10 | ↑0.3079 | Source ↗official | |
| MACHIAVELLIdeception_relative_random_pct | #41 / 50 | ↓95.6 | Source ↗official | |
| Pander Scoreconversational_absolute_pander_score | #12 / 20 | ↓16.43 | Source ↗official | |
| Pander Scoreinstructional_absolute_pander_score | #10 / 20 | ↓38.82 | Source ↗official | |
| RefusalBenchyouden_j | #5 / 19 | ↑0.3787 | Source ↗official | |
| SM-Benchadversarial | #66 / 79 | ↑76.83 | Source ↗official | |
| SM-Benchambiguous_interpretation | #43 / 79 | ↑84.08 | Source ↗official | |
| SM-Benchanti_hallucination | #68 / 79 | ↑80.23 | Source ↗official | |
| SM-Bencheq_boundaries | #32 / 79 | ↑67.28 | Source ↗official | |
| SM-Benchoverfit | #77 / 79 | ↑15.3 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #16 / 94 | ↑94.5 | Source ↗official | |
| VETO Misfired Alignmentmisfired_alignment_rate_pct | #17 / 25 | ↓9.9 | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.
Agent-ValueBench Moral Foundations (MFT08)
Agent-ValueBench HEXACO
| Dimension | Value | Distribution |
|---|---|---|
| Openness to experience | 5.5 | |
| Honesty-humility | 5.3 | |
| Extraversion | 6.1 | |
| Agreeableness | 6.5 | |
| Conscientiousness | 7.3 |