Model profile
GPT 5 Nano
Evidence summary
Safety. GPT 5 Nano has an estimated Safety rank of #42; its 90% source-sensitivity interval is #19–#175. Its behavior-only rank is #44; company governance moves the combined estimate to #42. Published Safety evidence spans 27 eval lineages and 7 of 7 components. Its strongest relative result is HELM Safety (simple_safety_tests, #1 of 80); its weakest is SimpleQA Verified (f1_score, #12 of 13).
Freedom. GPT 5 Nano has an estimated Freedom rank of #592; its 90% source-sensitivity interval is #411–#626. Published Freedom evidence spans 13 eval lineages and 1 of 1 components. Its strongest relative result is HELM Safety (xstest, #16 of 80); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #269 of 272).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gpt-5-nano
- OpenRouter ↗openai/gpt-5-nano
- System card ↗Family-level model document · OpenAI · first party
- Release source ↗direct research preview identity date
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 |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #97 / 361 | ↓0.5262 | Source ↗official | |
| Adversarial Poetry — AILuminate Baseline and Poetry ASRbaseline_asr | #1 / 24 | ↓0.82 | Source ↗official | |
| Adversarial Poetry — AILuminate Baseline and Poetry ASRpoetry_asr | #2 / 24 | ↓1.47 | Source ↗official | |
| AIRBench 2024 Safety Scenariossafety_scenarios | #6 / 80 | ↑0.878 | Source ↗official | |
| ANIMAscore | #10 / 22 | ↑0.708 | Source ↗official | |
| BioTIERpermit_compliance_pct | #41 / 52 | ↑97.6 | Source ↗official | |
| BioTIERrefuse_compliance_pct | #21 / 52 | ↑59.6 | Source ↗official | |
| CAIS Risk Indexagent_red_teaming | #37 / 49 | ↓88.5 | Source ↗official | |
| CAIS Risk Indexbioweapons_assistance | #33 / 54 | ↓71.3 | Source ↗official | |
| CAIS Risk Indexhle_overconfidence | #50 / 55 | ↓80 | Source ↗official | |
| CAIS Risk Indexmachiavelli | #2 / 51 | ↓79.4 | Source ↗official | |
| CAIS Risk Indexmask | #19 / 57 | ↓12.3 | Source ↗official | |
| CAIS Risk Indextextquests_harm | #1 / 54 | ↓2 | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #21 / 104 | ↓7.527 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #39 / 272 | ↑39.02 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #4 / 272 | ↑98 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #62 / 272 | ↑92.78 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #119 / 270 | ↑96.91 | Source ↗official | |
| HELM Safetyanthropic_red_team | #13 / 80 | ↑0.996 | Source ↗official | |
| HELM Safetybbq | #8 / 80 | ↑0.976 | Source ↗official | |
| HELM Safetyharmbench | #3 / 80 | ↑0.984 | Source ↗official | |
| HELM Safetysimple_safety_tests | #1 / 80 | ↑1 | Source ↗official | |
| HELM Safetyxstest | #16 / 80 | ↑0.976 | Source ↗official | |
| Human Pathogen Capabilities Test (HPCT) — overall refusalrefusal_rate_pct | #19 / 69 | ↑3.4 | Source ↗official | |
| MACHIAVELLIdeception_relative_random_pct | #1 / 50 | ↓79.4 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #9 / 47 | ↓5.067 | Source ↗self run | |
| MonitoringBench Full-Trajectory Monitorfull_trajectory_catch_rate_at_1pct_fpr_percent | #10 / 13 | ↑6 | Source ↗official | |
| PHAREbias_resistance_diagnostic | #55 / 66 | ↑0.347 | Source ↗official | |
| PHAREhallucination_resistance_diagnostic | #31 / 70 | ↑0.7637 | Source ↗official | |
| PHAREharm_resistance_diagnostic | #9 / 70 | ↑0.9741 | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #12 / 67 | ↑0.6964 | Source ↗official | |
| SimpleQA Verifiedf1_score | #12 / 13 | ↑14.4 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #115 / 133 | ↑6.4 | Source ↗official | |
| SpeciEvalland_animal_4ns | #40 / 133 | ↓4.35 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #59 / 133 | ↓4.68 | Source ↗official | |
| SpeciEvalspeciesism | #96 / 133 | ↓2.33 | Source ↗official | |
| StereoTales Harmful Associationsbenign_significant_association_score | #2 / 23 | ↑89.22 | Source ↗official | |
| TACbase_welfare_rate | #14 / 94 | ↑37.82 | Source ↗self run | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #56 / 94 | ↑89.5 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Adversarial Poetry — AILuminate Baseline and Poetry ASRbaseline_asr | #23 / 24 | ↑0.82 | Source ↗official | |
| Adversarial Poetry — AILuminate Baseline and Poetry ASRpoetry_asr | #23 / 24 | ↑1.47 | Source ↗official | |
| AIRBench 2024 Safety Scenariossafety_scenarios | #75 / 80 | ↓0.878 | Source ↗official | |
| BioTIERpermit_compliance_pct | #41 / 52 | ↑97.6 | Source ↗official | |
| BioTIERrefuse_compliance_pct | #32 / 52 | ↓59.6 | Source ↗official | |
| CAIS Risk Indexbioweapons_assistance | #22 / 54 | ↑71.3 | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #84 / 104 | ↑7.527 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #269 / 272 | ↓98 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #209 / 272 | ↓92.78 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #148 / 270 | ↓96.91 | Source ↗official | |
| HELM Safetyanthropic_red_team | #64 / 80 | ↓0.996 | Source ↗official | |
| HELM Safetyharmbench | #77 / 80 | ↓0.984 | Source ↗official | |
| HELM Safetysimple_safety_tests | #58 / 80 | ↓1 | Source ↗official | |
| HELM Safetyxstest | #16 / 80 | ↑0.976 | Source ↗official | |
| Human Pathogen Capabilities Test (HPCT) — overall refusalrefusal_rate_pct | #51 / 69 | ↓3.4 | Source ↗official | |
| PHAREharm_resistance_diagnostic | #62 / 70 | ↓0.9741 | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #56 / 67 | ↓0.6964 | Source ↗official | |
| SpeechMap model completioncomplete_pct | #96 / 181 | ↑56 | Source ↗official |