Grok 4.1 Fast (Reasoning) — benchmark results

Grok 4.1 Fast evaluated with reasoning enabled. Provider: xAI. Released 2025-11-20. Access: API.

Unified ELO 1662 ± 9, rank #338 of 1776 rated models, from 422 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Spanish Knowledge88.33Knowledge Average Score (%)99.5
EuroEval Portuguese Knowledge90.99Knowledge Average Score (%)99.2
UGI Leaderboard63.24UGI Score99.2
EuroEval Dutch NLU - DBRD93.57Sentiment classification Score (%)98.4
EuroEval French Knowledge84.95Knowledge Average Score (%)98.3
EuroEval Estonian Common Sense Reasoning82.16Common Sense Reasoning Average Score (%)98.2
EuroEval Italian Knowledge86.88Knowledge Average Score (%)98
EuroEval Ukrainian Knowledge88.88Knowledge Average Score (%)97.8
EuroEval French NLU - Allocine96.79Sentiment classification Score (%)97.7
EuroEval English NLU75.92NLU Average Score (%)97.6
EuroEval English NLU - ScaLA EN68.02Linguistic acceptability Score (%)97.6
EuroEval Latvian Knowledge84.18Knowledge Average Score (%)97.6

Interactive version: theaggregate.ai/model?slug=grok-4-1-fast-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.