Grok 4.20 Multi-agent
Grok 4.20 Multi-agent.
6
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
xAI Mar 2026
Grok 4.20 Multi-agent
Closed weights Flagship
No Epoch Capabilities Index score yet
- Human Pathogen Capabilities Test v2 (HPCT v2) 53.6% #36 /71
- DTBench 84.5% #43 /178
- BullshitBench V2 67% #22 /122
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BullshitBench | 67.3% | #10 of 107 | Official leaderboard | |
| BullshitBench V2 | 67% | #22 of 122 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| DTBench | 84.5% | #43 of 178 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Human Pathogen Capabilities Test v2 (HPCT v2) | 53.6% | #36 of 71 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Conceptual Reasoning Index | 55.6 | #49 of 149 | Official leaderboard | |
| ACCoRD | 69.6 | #53 of 150 | Official leaderboard |