Model profile
Grok 3
Evidence summary
Safety. Grok 3 has an estimated Safety rank of #181; its 90% source-sensitivity interval is #56–#259. Its behavior-only rank is #187; company governance moves the combined estimate to #181. Published Safety evidence spans 19 eval lineages and 7 of 7 components. Its strongest relative result is Emergent Collusion (high_illegality_game_rate, #1 of 13); its weakest is SOSBench (biology_pvr, #23 of 23).
Freedom. Grok 3 has an estimated Freedom rank of #3; its 90% source-sensitivity interval is #9–#58. Published Freedom evidence spans 11 eval lineages and 1 of 1 components. Its strongest relative result is Cisco AI Defense Rolling Single-Turn Leaderboard (single_turn_attack_success_rate, #2 of 104); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #124 of 248).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗grok-3
- OpenRouter ↗x-ai/grok-3
- Official model documentation ↗Family-level model document · xai · 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 | #240 / 345 | ↓0.8732 | Source ↗official | |
| AIRBench 2024 Safety Scenariossafety_scenarios | #64 / 80 | ↑0.513 | Source ↗official | |
| CAIS Risk Indexpolitical_manipulation | #20 / 48 | ↓45.6 | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #103 / 104 | ↓84.15 | Source ↗official | |
| Confabulationsconfabulation_rate | #19 / 52 | ↓17.82 | Source ↗official | |
| Emergent Collusionhigh_illegality_game_rate | #1 / 13 | ↓0.19 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #91 / 248 | ↑19.38 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #125 / 248 | ↑88 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #211 / 248 | ↑40.56 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #241 / 246 | ↑61.75 | Source ↗official | |
| HELM Safetyanthropic_red_team | #72 / 80 | ↑0.955 | Source ↗official | |
| HELM Safetybbq | #41 / 80 | ↑0.936 | Source ↗official | |
| HELM Safetyharmbench | #75 / 80 | ↑0.453 | Source ↗official | |
| HELM Safetysimple_safety_tests | #62 / 80 | ↑0.968 | Source ↗official | |
| HELM Safetyxstest | #33 / 80 | ↑0.964 | Source ↗official | |
| HUMAINE Trust, Ethics and Safetytrust_ethics_safety_score | #5 / 54 | ↑29.14 | Source ↗official | |
| PHAREbias_resistance_diagnostic | #65 / 66 | ↑0.2324 | Source ↗official | |
| PHAREhallucination_resistance_diagnostic | #36 / 70 | ↑0.7512 | Source ↗official | |
| PHAREharm_resistance_diagnostic | #51 / 70 | ↑0.8968 | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #66 / 67 | ↑0.2577 | Source ↗official | |
| SOSBenchbiology_pvr | #23 / 23 | ↓0.894 | Source ↗official | |
| SOSBenchchemistry_pvr | #18 / 23 | ↓0.638 | Source ↗official | |
| SOSBenchmedicine_pvr | #21 / 23 | ↓0.86 | Source ↗official | |
| SOSBenchpharmacology_pvr | #21 / 23 | ↓0.954 | Source ↗official | |
| SOSBenchphysics_pvr | #20 / 23 | ↓0.804 | Source ↗official | |
| SOSBenchpsychology_pvr | #23 / 23 | ↓0.89 | Source ↗official | |
| SpeciesismBenchexplicit_speciesism_scale | #6 / 7 | ↓2.493 | Source ↗official | |
| SpeciesismBenchmorally_wrong_rate | #4 / 8 | ↑38.78 | Source ↗official | |
| SpeciesismBenchspeciesism_recognition_rate | #3 / 8 | ↑89.13 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #119 / 123 | ↑6.255 | Source ↗official | |
| SpeciEvalland_animal_4ns | #114 / 123 | ↓5.025 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #104 / 123 | ↓5.05 | Source ↗official | |
| SpeciEvalspeciesism | #114 / 123 | ↓2.865 | Source ↗official | |
| TukaBenchafri_jbb_cultural_asr | #6 / 6 | ↓35.6 | Source ↗official | |
| TukaBenchafri_jbb_harm_asr | #6 / 6 | ↓29.3 | Source ↗official | |
| TukaBenchafrijail_mono_asr | #6 / 6 | ↓30.2 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #21 / 94 | ↑94.2 | 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 |
|---|---|---|---|---|
| AIRBench 2024 Safety Scenariossafety_scenarios | #17 / 80 | ↓0.513 | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #2 / 104 | ↑84.15 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #124 / 248 | ↓88 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #37 / 248 | ↓40.56 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #6 / 246 | ↓61.75 | Source ↗official | |
| HELM Safetyanthropic_red_team | #9 / 80 | ↓0.955 | Source ↗official | |
| HELM Safetyharmbench | #6 / 80 | ↓0.453 | Source ↗official | |
| HELM Safetysimple_safety_tests | #18 / 80 | ↓0.968 | Source ↗official | |
| HELM Safetyxstest | #33 / 80 | ↑0.964 | Source ↗official | |
| PHAREharm_resistance_diagnostic | #20 / 70 | ↓0.8968 | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #2 / 67 | ↓0.2577 | Source ↗official | |
| SOSBenchbiology_pvr | #1 / 23 | ↑0.894 | Source ↗official | |
| SOSBenchchemistry_pvr | #6 / 23 | ↑0.638 | Source ↗official | |
| SOSBenchmedicine_pvr | #3 / 23 | ↑0.86 | Source ↗official | |
| SOSBenchpharmacology_pvr | #3 / 23 | ↑0.954 | Source ↗official | |
| SOSBenchphysics_pvr | #4 / 23 | ↑0.804 | Source ↗official | |
| SOSBenchpsychology_pvr | #1 / 23 | ↑0.89 | Source ↗official | |
| TukaBenchafri_jbb_cultural_asr | #1 / 6 | ↑35.6 | Source ↗official | |
| TukaBenchafri_jbb_harm_asr | #1 / 6 | ↑29.3 | Source ↗official | |
| TukaBenchafrijail_mono_asr | #1 / 6 | ↑30.2 | Source ↗official | |
| UGI Leaderboard — base-model willingnesswillingness_adherence_score | #6 / 156 | ↑8 | Source ↗official | |
| UGI Leaderboard — base-model willingnesswillingness_direct_score | #21 / 156 | ↑5 | 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.