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.
Aggregate Rating 1581 ± 20, rank #762 of 2168 rated models, from 64 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI Leaderboard | 51.77 | UGI Score | 92.2 |
| UGI - Writing | 47.15 | Writing Score | 85.5 |
| UGI - Natural Intelligence | 40.76 | NatInt Score | 85.3 |
| AA Humanity's Last Exam | 24.51 | Accuracy (%) | 71.2 |
| AA Global-MMLU-Lite - Portuguese | 89.58 | Accuracy (%) | 69.1 |
| AA Global-MMLU-Lite - Spanish | 90 | Accuracy (%) | 69.1 |
| AA GPQA Diamond | 78.48 | Accuracy (%) | 64.5 |
| AA Global-MMLU-Lite - Burmese | 78.58 | Accuracy (%) | 64.5 |
| Tau2-Bench Telecom | 69.59 | Success Rate (%) | 64.1 |
| AA TAU-2 Bench | 69.59 | Accuracy (%) | 62.6 |
| AA Terminal-Bench Hard | 21.97 | Accuracy (%) | 61.9 |
| AA Global-MMLU-Lite - Yoruba | 61.75 | Accuracy (%) | 61.8 |
Interactive version: theaggregate.ai/model?slug=grok-4-20-0309-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.