Model profile
Grok 4.6
xAIdeveloper
2026-08-12release date
#151 / 317overall rank
6eval lineages
Evidence summary
Grok 4.6 has an estimated overall rank of #151; its 90% source-sensitivity interval is #22–#273. Its behavior-only rank is #149; company governance moves the combined estimate to #151. Published evidence spans 6 evals and 5 of 7 behavior components. Its strongest relative result is SM-Bench (anti_hallucination, #1 of 81); its weakest is TAC (base_welfare_rate, #74 of 79).
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
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 | #10 / 331 | ↓0.24 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #25 / 35 | ↓8.9 | Source ↗official | |
| Manager Coercion Benchfabrication_rate | #1 / 15 | ↓0 | Source ↗official | |
| Olam Social Poker — Social Lie Ratesocial_lie_rate_per_10000_turns | #9 / 22 | ↓6 | Source ↗official | |
| Pander Scoreconversational_absolute_pander_score | #10 / 22 | ↓13.82 | Source ↗official | |
| Pander Scoreinstructional_absolute_pander_score | #11 / 22 | ↓33.62 | Source ↗official | |
| SM-Benchadversarial | #40 / 81 | ↑81.95 | Source ↗official | |
| SM-Benchambiguous_interpretation | #17 / 81 | ↑90.18 | Source ↗official | |
| SM-Benchanti_hallucination | #1 / 81 | ↑100 | Source ↗official | |
| SM-Bencheq_boundaries | #8 / 81 | ↑74.16 | Source ↗official | |
| SM-Benchoverfit | #28 / 81 | ↑80.87 | Source ↗official | |
| TACbase_welfare_rate | #74 / 79 | ↑16.67 | Source ↗official |