Grok Code Fast 1: benchmark results
xAI's fast, low-cost reasoning model for agentic coding, with a 256K context and ~70.8% SWE-bench Verified (August 2025). Provider: xAI. Released 2025-08-20. Access: API.
Aggregate Rating 1637 ± 10, rank #337 of 1656 rated models, from 168 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLVM-Bench (SWE-agent) | 10.87 | Resolved rate (%; share of the 423 validated LLVM issues, ve | 100 |
| AA Omniscience - Software Engineering (SWE) - Dart | 34 | Accuracy (%) | 89.9 |
| AA Omniscience - Software Engineering (SWE) - R | 30 | Accuracy (%) | 88.7 |
| Software Engineering Arena - Model Arena | 1002 | Elo Rating | 86.4 |
| AA Omniscience - Software Engineering (SWE) - PHP | 40 | Accuracy (%) | 85.2 |
| GSMA Open-Telco - TeleLogs | 61 | Score (%) | 83.7 |
| AA Omniscience - Software Engineering (SWE) - Go | 30.61 | Accuracy (%) | 83.1 |
| AA Omniscience - Software Engineering (SWE) - Python | 32 | Accuracy (%) | 82.9 |
| Tinybird AI SQL Benchmark - First-Attempt Success Rate | 98 | Questions answered with a valid query on the first attempt ( | 80.5 |
| AA Omniscience - Software Engineering (SWE) - Julia | 24 | Accuracy (%) | 80.2 |
| SnakeBench | 27.9 | TrueSkill Rating | 79.1 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 32.22 | Accuracy (%) | 78.3 |
Interactive version: theaggregate.ai/model?slug=grok-code-fast-1 · How It Works · Data refreshed daily, snapshot 2026-10-20.