Grok 4 Fast — benchmark results
xAI's speed- and cost-optimized Grok 4 variant with a 2M-token context. Provider: xAI. Released 2025-09-19. Access: API.
Unified ELO 1649 ± 21, rank #371 of 1776 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SnakeBench | 33.2 | TrueSkill Rating | 95.1 |
| GSMA Open-Telco - TeleLogs | 75 | Score (%) | 94.2 |
| GSMA Open-Telco - TeleQnA | 83.6 | Score (%) | 92.4 |
| GSMA Open-Telco - srsRAN-Bench | 84 | Score (%) | 87.8 |
| LOL Arena | 47.1 | Win Rate (%) | 87.5 |
| GSMA Open-Telco LLM Leaderboard | 68.42 | Average Score (%) | 87.2 |
| CritPt | 2.9 | Accuracy (self-reported) | 85.2 |
| AA-LCR | 64.7 | Score (self-reported) | 83.2 |
| AI for Education Pedagogy - Maths | 87.3 | Accuracy (%) | 83.2 |
| Fiction.LiveBench | 75 | Accuracy (%) | 82.5 |
| AI for Education Pedagogy - Technology | 83.96 | Accuracy (%) | 81.8 |
| FormationEval | 96 | Accuracy (%) | 81.7 |
Interactive version: theaggregate.ai/model?slug=grok-4-fast · How the rankings work · Data refreshed daily, snapshot 2026-07-22.