xAI · model
Grok 4.20 Multi-agent benchmark scores
As of 2026-11-18, Grok 4.20 Multi-agent (xAI) has measured scores on 1 benchmark and estimated scores on 12 more.
| Benchmark | Score | Source |
|---|---|---|
| FailureSensorIQ | 68.0% | estimated ± 1.7 pp, high confidence |
| Chess Puzzles | 48.3% | estimated ± 12.3 pp, low confidence |
| Mystery Game Puzzles | 45.3% | estimated ± 14.6 pp, low confidence |
| NYT Connections | 89.6% | measured |
| SpireClimb | 7.0% | estimated ± 8.8 pp, medium confidence |
| StealthMark | 58.3% | estimated ± 10.7 pp, low confidence |
| SkillsBench official leaderboard (BenchFlow) | 55.5% | estimated ± 6.1 pp, medium confidence |
| BinaryAudit | 35.8% | estimated ± 12.1 pp, low confidence |
| OTelBench | 22.5% | estimated ± 6.6 pp, medium confidence |
| FACTS Multimodal | 50.2% | estimated ± 4.0 pp, high confidence |
| BlenderWorld (text-only) | 81.8% | estimated ± 4.3 pp, medium confidence |
| Cookie-Bench | 89.2% | estimated ± 4.8 pp, medium confidence |
| ExploitBench Internal Port | 15.3% | estimated ± 13.8 pp, low confidence |