Grok Build 0.1: benchmark results
xAI's Grok Build 0.1 agentic coding model behind the Grok Build CLI. Provider: xAI. Released 2026-05-29. Access: API.
Aggregate Rating 1752 ± 16, rank #117 of 1656 rated models, from 89 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| PinchBench - 147 Tasks - OpenClaw 2026.5.4 (325df3e) | 92.07 | Best Official Run Score (%) | 95.7 |
| Tinybird AI SQL Benchmark - First-Attempt Success Rate | 100 | Questions answered with a valid query on the first attempt ( | 94 |
| AA-Omniscience Accuracy | 51.52 | Accuracy (%) | 90.5 |
| AI Chess Leaderboard (Reasoning) | 1380 | Elo | 89.2 |
| AA GPQA Diamond | 89.49 | Accuracy (%) | 87.6 |
| AA-Omniscience Index - Health | 0.6 | Omniscience Index | 86.3 |
| AA-Omniscience Index - Software Engineering (SWE) - C | 68 | Omniscience Index | 85.8 |
| AA-Omniscience Index - Software Engineering (SWE) - JavaScript | 50 | Omniscience Index | 85.2 |
| AA Humanity's Last Exam | 38.28 | Accuracy (%) | 85 |
| AA-Omniscience Index - Software Engineering (SWE) - Java | 8 | Omniscience Index | 82.8 |
| AA Omniscience | 6.37 | Score | 82.7 |
| AA-Omniscience Index - Software Engineering (SWE) - R | 22 | Omniscience Index | 82.7 |
Interactive version: theaggregate.ai/model?slug=grok-build-0-1 · How It Works · Data refreshed daily, snapshot 2026-10-20.