Grok 4.20 0309 (Non-reasoning): benchmark results
March 9, 2026 Grok 4.20 snapshot evaluated with reasoning disabled. Provider: xAI. Released 2026-03-09. Access: API.
Unified ELO 1552 ± 1, rank #627 of 1761 rated models, from 45 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI Leaderboard | 51.77 | UGI Score | 92.8 |
| UGI - Writing | 47.15 | Writing Score | 87.1 |
| UGI - Natural Intelligence | 40.76 | NatInt Score | 86.9 |
| AA Humanity's Last Exam | 24.51 | Accuracy (%) | 76.7 |
| AA Omniscience - Law | 21.4 | Accuracy (%) | 72.3 |
| AA Global-MMLU-Lite - Portuguese | 89.58 | Accuracy (%) | 69.4 |
| AA Global-MMLU-Lite - Spanish | 90 | Accuracy (%) | 69.4 |
| AA Omniscience - Humanities & Social Sciences | 26.6 | Accuracy (%) | 68.5 |
| AA Omniscience - Health | 25.43 | Accuracy (%) | 67.8 |
| AA Omniscience - Software Engineering (SWE) | 35.14 | Accuracy (%) | 66.9 |
| AA-Omniscience Accuracy | 26.05 | Accuracy (%) | 66.4 |
| AA Global-MMLU-Lite - Burmese | 78.58 | Accuracy (%) | 64.9 |
Interactive version: theaggregate.ai/model?slug=grok-4-20-0309-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.