SpaceXAI

Grok 4 Fast (Non-Reasoning)

Released 2025-09-19 · Data snapshot 2026-10-26

Overall score

47.0

Ranked #62

Benchmark coverage

19.2%

5 third-party benchmarks

Context window

—

tokens

Input price

—

per million tokens

Output price

—

per million tokens

Dimension performance

Human preference

60.7

Office

43.5

Above averageBelow averageAnchored at 50 (reference models’ average); every 15 points ≈ one standard deviation

Office3 items

Tax Eval v2non-reasoning71.58

Corporate Finance v2non-reasoning58.39

MedCodenon-reasoning30.04

Knowledge1 items

MMLU-Pronon-reasoning70.34

Human preference1 items

LMArena Human Blind Votenon-reasoning1418.4986

Multiple reasoning tiers of the same benchmark take the best value; raw scores have different scales and are not comparable across benchmarks.