Grok 4 Fast (Non-reasoning) — benchmark results
Grok 4 Fast evaluated with reasoning disabled. Provider: xAI. Released 2025-09-19. Access: API.
Unified ELO 1579 ± 23, rank #532 of 1776 rated models, from 71 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SpeechMap Compliance | 98 | % Requests Completed | 98.5 |
| UGI - Writing | 43.04 | Writing Score | 82.9 |
| UGI Leaderboard | 45.76 | UGI Score | 82.3 |
| UGI - Natural Intelligence | 33.1 | NatInt Score | 79.9 |
| AI Chess Leaderboard (Reasoning) | 754 | Elo | 64.4 |
| AA TAU-2 Bench | 63.74 | Accuracy (%) | 58.6 |
| Vals AI MedScribe | 79.72 | Accuracy (%) | 56.9 |
| Episodic Memory | 60.2 | Simple Recall (%) | 55 |
| AA Omniscience - Humanities & Social Sciences | 20.4 | Accuracy (%) | 54 |
| AA Omniscience - Software Engineering (SWE) - R | 12 | Accuracy (%) | 52 |
| Artificial Analysis Intelligence Index | 16.47 | Intelligence Index | 51.7 |
| Vals AI TaxEval v2 | 71.58 | Accuracy (%) | 49.2 |
Interactive version: theaggregate.ai/model?slug=grok-4-fast-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.