Model profile
Grok 4.6
Evidence summary
Safety. Grok 4.6 has an estimated Safety rank of #175; its 90% source-sensitivity interval is #52–#288. Its behavior-only rank is #173; company governance moves the combined estimate to #175. Published Safety evidence spans 15 eval lineages and 6 of 7 components. Its strongest relative result is SM-Bench (anti_hallucination, #1 of 92); its weakest is BioSecBench-Refusal V2 (redteam_refusal_pct, #6 of 6).
Freedom. Grok 4.6 has an estimated Freedom rank of #88; its 90% source-sensitivity interval is #46–#423. Published Freedom evidence spans 4 eval lineages and 1 of 1 components. Its strongest relative result is SM-Bench (eq_boundaries, #11 of 92); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #251 of 270).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗grok-4-6
- OpenRouter ↗x-ai/grok-4.6
- Official model page ↗Exact model document · xAI · 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 |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #15 / 358 | ↓0.24 | Source ↗official | |
| BioSecBench-Refusal V2redteam_refusal_pct | #6 / 6 | ↑42.39 | Source ↗official | |
| BioSecBench-Refusal V2routine_compliance_pct | #2 / 6 | ↑53.57 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #22 / 122 | ↑0.61 | Source ↗official | |
| CheatBench direct cheating propensitybiology_bioinformatics_cheating_rate_pct | #5 / 8 | ↓100 | Source ↗official | |
| CheatBench direct cheating propensityboard_games_cheating_rate_pct | #6 / 8 | ↓100 | Source ↗official | |
| CheatBench direct cheating propensitycreative_writing_cheating_rate_pct | #6 / 8 | ↓100 | Source ↗official | |
| CheatBench direct cheating propensityknowledge_work_cheating_rate_pct | #2 / 8 | ↓40 | Source ↗official | |
| CheatBench direct cheating propensitymathematical_research_cheating_rate_pct | #7 / 8 | ↓98 | Source ↗official | |
| CheatBench direct cheating propensitymenial_computation_cheating_rate_pct | #4 / 8 | ↓100 | Source ↗official | |
| CheatBench direct cheating propensitymultimodal_cheating_rate_pct | #7 / 8 | ↓100 | Source ↗official | |
| CheatBench direct cheating propensitysoftware_engineering_cheating_rate_pct | #5 / 8 | ↓50 | Source ↗official | |
| CheatBench direct cheating propensitysvg_competition_cheating_rate_pct | #7 / 8 | ↓100 | Source ↗official | |
| Claude system cards — Gray Swan Q1+Q2 indirect prompt injection k=15attack_success_probability_k15_pct | #11 / 12 | ↓50.2 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #10 / 270 | ↑64.86 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #214 / 270 | ↑76 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #10 / 270 | ↑99.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #123 / 268 | ↑96.73 | Source ↗official | |
| Google Gemini 3.8 launch — Gray Swan indirect prompt injection k=15attack_success_probability_k15_pct | #13 / 15 | ↓51.8 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #35 / 45 | ↓8.9 | Source ↗official | |
| Manager Coercion Benchfabrication_rate | #1 / 15 | ↓0 | Source ↗official | |
| Olam Diplomacy — Broken Promise Ratebroken_promise_rate_pct | #12 / 19 | ↓15.8 | Source ↗official | |
| Olam Social Poker — Social Lie Ratesocial_lie_rate_per_10000_turns | #9 / 24 | ↓6 | Source ↗official | |
| Pander Scoreconversational_absolute_pander_score | #13 / 26 | ↓13.82 | Source ↗official | |
| Pander Scoreinstructional_absolute_pander_score | #14 / 26 | ↓33.62 | Source ↗official | |
| SM-Benchadversarial | #46 / 92 | ↑81.95 | Source ↗official | |
| SM-Benchambiguous_interpretation | #20 / 92 | ↑90.18 | Source ↗official | |
| SM-Benchanti_hallucination | #1 / 92 | ↑100 | Source ↗official | |
| SM-Bencheq_boundaries | #11 / 92 | ↑74.16 | Source ↗official | |
| SM-Benchoverfit | #37 / 92 | ↑80.87 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #23 / 131 | ↑6.98 | Source ↗official | |
| SpeciEvalland_animal_4ns | #101 / 131 | ↓4.78 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #69 / 131 | ↓4.75 | Source ↗official | |
| SpeciEvalspeciesism | #113 / 131 | ↓2.62 | Source ↗official | |
| TACbase_welfare_rate | #87 / 92 | ↑16.67 | Source ↗official | |
| Vals AI Cheating Auditbiomystery_bench_cheating_attempt_rate_pct | #6 / 9 | ↓6.667 | 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 |
|---|---|---|---|---|
| BioSecBench-Refusal V2redteam_refusal_pct | #1 / 6 | ↓42.39 | Source ↗official | |
| BioSecBench-Refusal V2routine_compliance_pct | #2 / 6 | ↑53.57 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #56 / 270 | ↓76 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #251 / 270 | ↓99.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #143 / 268 | ↓96.73 | Source ↗official | |
| SM-Benchadversarial | #45 / 92 | ↓81.95 | Source ↗official | |
| SM-Bencheq_boundaries | #11 / 92 | ↑74.16 | Source ↗official | |
| SM-Benchoverfit | #37 / 92 | ↑80.87 | Source ↗official | |
| SpeechMap model completioncomplete_pct | #29 / 181 | ↑83.6 | Source ↗official |