Grok 4.1 Fast Benchmark Details

Grok 4.1 Fast currently shows benchmark results led by MMLU Pro (25 / 126, score 85), LiveCodeBench (25 / 120, score 82), τ²-Bench (10 / 40, score 82.71).

Benchmark Results

Grok 4.1 Fast

Benchmark Results

General Knowledge

5 evaluations

Benchmark / mode

Score

Rank/total

MMLU Pro

25 / 126

GPQA Diamond

51 / 180

LiveBench

Standard Mode

33.45

114 / 115

LiveBench

Thinking Enabled

69 / 115

HLE

17.60

121 / 164

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

25 / 120

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

AIME2025

40 / 106

AI Agent - Tool Usage

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal-Bench

30 / 35

常识推理

1 evaluations

Benchmark / mode

Score

Rank/total

Simple Bench

Standard Mode

21 / 63

Agent Level Benchmark

2 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench - Telecom

94.74

15 / 35

τ²-Bench

82.71

10 / 40

Instruction Following

1 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

27 / 29

Claw-style Agent Evaluation

2 evaluations

Benchmark / mode

Score

Rank/total

Claw Bench

Thinking EnabledTools

88.60

12 / 29

Pinch Bench

Thinking EnabledTools

82.40

20 / 37

Compare with other models