Model profile
Grok 4.20 Multi Agent
xAIdeveloper
2026-03-10release date
#29 / 267overall rank
4eval lineages
Evidence summary
Grok 4.20 Multi Agent has an estimated overall rank of #29; its 90% source-sensitivity interval is #11–#162. Its behavior-only rank is #15; company governance moves the combined estimate to #29. Published evidence spans 4 evals and 4 of 7 behavior components. Its strongest relative result is SM-Bench (eq_boundaries, #3 of 73); its weakest is SM-Bench (adversarial, #52 of 73).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗x-ai/grok-4.20-multi-agent
- Official model documentation ↗Family-level model document · xai · 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 |
|---|---|---|---|---|---|
| BullshitBench v2clear_pushback_rate | #12 / 105 | 0.655 | ↑ higher | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #47 / 105 | 33 | ↓ lower | Source ↗official | |
| DystopiaBenchbasaglia_score | #22 / 50 | 60.2 | ↓ lower | Source ↗official | |
| DystopiaBenchbaudrillard_score | #29 / 50 | 61.77 | ↓ lower | Source ↗official | |
| DystopiaBenchhuxley_score | #31 / 50 | 74 | ↓ lower | Source ↗official | |
| DystopiaBenchlaguardia_score | #23 / 50 | 65.3 | ↓ lower | Source ↗official | |
| DystopiaBenchorwell_score | #33 / 50 | 72.9 | ↓ lower | Source ↗official | |
| DystopiaBenchpetrov_score | #32 / 50 | 74.4 | ↓ lower | Source ↗official | |
| SM-Benchadversarial | #52 / 73 | 79.02 | ↑ higher | Source ↗official | |
| SM-Benchambiguous_interpretation | #3 / 73 | 92.86 | ↑ higher | Source ↗official | |
| SM-Benchanti_hallucination | #27 / 73 | 94.76 | ↑ higher | Source ↗official | |
| SM-Bencheq_boundaries | #3 / 73 | 83.99 | ↑ higher | Source ↗official | |
| SM-Benchoverfit | #16 / 73 | 84.7 | ↑ higher | Source ↗official |