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.
Unified ELO 1853 ± 25, rank #103 of 1776 rated models, from 50 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Health | 48.9 | Accuracy (%) | 99.1 |
| AA Omniscience - Science, Engineering & Mathematics | 52.1 | Accuracy (%) | 99 |
| AA Omniscience - Business | 44.8 | Accuracy (%) | 96.9 |
| AA Omniscience - Humanities & Social Sciences | 50.2 | Accuracy (%) | 96.5 |
| AA-Omniscience Accuracy | 51.4 | Accuracy (%) | 96.4 |
| AA Omniscience - Law | 48.6 | Accuracy (%) | 95.8 |
| AA Omniscience - Software Engineering (SWE) - C | 83 | Accuracy (%) | 95.1 |
| AA Omniscience - Software Engineering (SWE) - Java | 55 | Accuracy (%) | 94.9 |
| AA Humanity's Last Exam | 35.96 | Accuracy (%) | 94.1 |
| AA Omniscience - Software Engineering (SWE) - R | 58 | Accuracy (%) | 93.4 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 72.73 | Accuracy (%) | 93.2 |
| AA SciCode | 50.23 | Accuracy (%) | 93.2 |
Interactive version: theaggregate.ai/model?slug=grok-build-0-1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.