Grok 4.20 (Non-reasoning): benchmark results
Grok 4.20 evaluated with reasoning disabled. Provider: xAI. Released 2026-03-10. Access: API.
Aggregate Rating 1608 ± 18, rank #688 of 2168 rated models, from 45 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BenchTable - Tech | 79.6 | Weighted Score (%) | 85 |
| K-Bench | 98.32 | Overall (%, Default v1 prompt) | 75.4 |
| BenchTable - Utility | 63.4 | Weighted Score (%) | 70.3 |
| BenchTable | 58.7 | Total Score (%) | 68.6 |
| ZeroBench | 10 | Score (%) | 61 |
| Design Arena (Website) | 1220 | Elo | 60.7 |
| BenchTable - Reasoning | 46.4 | Weighted Score (%) | 58.7 |
| Design Arena (UI Components) | 1189 | Elo | 53.5 |
| CLBench - Domain Knowledge Reasoning | 19.5 | Solving Rate (%) | 52.9 |
| Design Arena (Game Dev) | 1174 | Elo | 52.2 |
| Design Arena (Data Viz) | 1199 | Elo | 51.7 |
| Design Arena (3D) | 1152 | Elo | 50.9 |
Interactive version: theaggregate.ai/model?slug=grok-4-20-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.