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 1627 ± 1, rank #189 of 1392 rated models, from 73 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SnakeBench | 33.2 | TrueSkill Rating | 95.1 |
| GSMA Open-Telco - TeleLogs | 75 | Score (%) | 93.2 |
| GSMA Open-Telco - TeleQnA | 83.6 | Score (%) | 92.6 |
| YapBench | 70.2 | YapIndex (lower is better) | 90.3 |
| Diplomacy: Betrayal Tendency | 0 | Betrayal Rate (%) | 87.5 |
| LOL Arena | 47.1 | Win Rate (%) | 87.5 |
| GSMA Open-Telco - srsRAN-Bench | 84 | Score (%) | 86.9 |
| GSMA Open-Telco LLM Leaderboard | 68.42 | Average Score (%) | 85.2 |
| Fiction.LiveBench | 75 | Accuracy (%) | 82.1 |
| GSMA Open-Telco - ORAN-Bench | 83.33 | Score (%) | 81.8 |
| FormationEval | 96 | Accuracy (%) | 81.7 |
| Chess Bench LLM | 1220 | Lichess Rating | 81.1 |
Interactive version: theaggregate.ai/model?slug=grok-4-fast · How It Works · Data refreshed daily, snapshot 2026-09-05.