Grok 4.20 0309 v2: benchmark results
Provider: xAI. Released 2026-03-09. Access: API.
Aggregate Rating 1757 ± 37, rank #162 of 10916 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA IFBench | 81.22 | Accuracy (%) | 98.9 |
| AA GPQA Diamond | 91.11 | Accuracy (%) | 91.7 |
| AA TAU-2 Bench | 92.98 | Accuracy (%) | 89.1 |
| Tau2-Bench Telecom | 92.98 | Success Rate (%) | 88.9 |
| AA Terminal-Bench Hard | 37.88 | Accuracy (%) | 84.9 |
| AA Humanity's Last Exam | 34.52 | Accuracy (%) | 80.1 |
| AA CritPt | 6.57 | Accuracy (%) | 72.6 |
| AA MMMU-Pro | 74.57 | Accuracy (%) | 60 |
| AA Long Context Reasoning | 69 | Accuracy (%) | 58.1 |
Interactive version: theaggregate.ai/model?slug=grok-4-20-0309-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.