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

BenchmarkScoreMetricPercentile
SpeechMap Compliance98% Requests Completed98.5
UGI - Writing43.04Writing Score82.9
UGI Leaderboard45.76UGI Score82.3
UGI - Natural Intelligence33.1NatInt Score79.9
AI Chess Leaderboard (Reasoning)754Elo64.4
AA TAU-2 Bench63.74Accuracy (%)58.6
Vals AI MedScribe79.72Accuracy (%)56.9
Episodic Memory60.2Simple Recall (%)55
AA Omniscience - Humanities & Social Sciences20.4Accuracy (%)54
AA Omniscience - Software Engineering (SWE) - R12Accuracy (%)52
Artificial Analysis Intelligence Index16.47Intelligence Index51.7
Vals AI TaxEval v271.58Accuracy (%)49.2

Interactive version: theaggregate.ai/model?slug=grok-4-fast-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.