Model profile
O1
Evidence summary
O1 has an estimated overall rank of #78; its 90% source-sensitivity interval is #21–#156. Its behavior-only rank is #82; company governance moves the combined estimate to #78. Published evidence spans 16 evals and 6 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #12 of 260); its weakest is CAIS Risk Index (hle_overconfidence, #47 of 49).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗o1
- OpenRouter ↗openai/o1
- System card ↗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 | Better | Source |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #96 / 311 | 0.6925 | ↓ lower | Source ↗official | |
| AbstentionBenchanswer_unknown_f1 | #7 / 20 | 0.8917 | ↑ higher | Source ↗official | |
| AbstentionBenchfalse_premise_f1 | #1 / 20 | 0.7687 | ↑ higher | Source ↗official | |
| AbstentionBenchstale_f1 | #8 / 20 | 0.646 | ↑ higher | Source ↗official | |
| AbstentionBenchsubjective_f1 | #5 / 20 | 0.7654 | ↑ higher | Source ↗official | |
| AbstentionBenchunderspecified_context_f1 | #6 / 20 | 0.6907 | ↑ higher | Source ↗official | |
| AbstentionBenchunderspecified_intent_f1 | #3 / 20 | 0.7694 | ↑ higher | Source ↗official | |
| AIRBench 2024 Safety Scenariossafety_scenarios | #21 / 80 | 0.8 | ↑ higher | Source ↗official | |
| BlueBench AttaQ-100attaq_harmlessness_reward_pct | #15 / 18 | 82.96 | ↑ higher | Source ↗official | |
| CAIS Risk Indexbioweapons_assistance | #25 / 48 | 68.1 | ↓ lower | Source ↗official | |
| CAIS Risk Indexhle_overconfidence | #47 / 49 | 83 | ↓ lower | Source ↗official | |
| CAIS Risk Indexmask | #33 / 51 | 40.7 | ↓ lower | Source ↗official | |
| Confabulationsconfabulation_rate | #10 / 52 | 10.89 | ↓ lower | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #113 / 260 | 17.83 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #12 / 260 | 96.33 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #32 / 260 | 96.11 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #103 / 258 | 97.41 | ↑ higher | Source ↗official | |
| FORTRESSaverage_risk_score | #17 / 49 | 19.38 | ↓ lower | Source ↗official | |
| FORTRESSover_refusal_score | #25 / 46 | 5.05 | ↓ lower | Source ↗official | |
| HELM Safetyanthropic_red_team | #50 / 80 | 0.983 | ↑ higher | Source ↗official | |
| HELM Safetybbq | #9 / 80 | 0.973 | ↑ higher | Source ↗official | |
| HELM Safetyharmbench | #12 / 80 | 0.963 | ↑ higher | Source ↗official | |
| HELM Safetysimple_safety_tests | #32 / 80 | 0.99 | ↑ higher | Source ↗official | |
| HELM Safetyxstest | #24 / 80 | 0.97 | ↑ higher | Source ↗official | |
| HUMAINE Trust, Ethics and Safetytrust_ethics_safety_score | #45 / 54 | 24.33 | ↑ higher | Source ↗official | |
| MASKlying_probability_pct | #28 / 53 | 40.73 | ↓ lower | 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.