Grok 4.1 Fast Benchmark Details

Grok 4.1 Fast currently shows benchmark results led by MMLU Pro (27 / 133, score 85), LiveCodeBench (27 / 126, score 82), τ²-Bench (10 / 43, score 82.71).

Benchmark Results

Grok 4.1 Fast

Benchmark Results

General Knowledge

4 evaluations

Benchmark / mode

Score

Rank/total

MMLU Pro

Thinking Mode

27 / 133

LiveBench

Standard Mode

33.45

114 / 115

LiveBench

Thinking Mode

69 / 115

HLE

Thinking Mode

17.60

138 / 181

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Thinking Mode

85 / 224

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Thinking Mode

27 / 126

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

AIME2025

Thinking Mode

40 / 106

Writing and Creative Capabilities

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

1324.40

65 / 99

AI Agent - Tool Usage

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal-Bench

Thinking ModeTools

30 / 35

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleBench

Standard Mode

26 / 67

Agent Level Benchmark

2 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench - Telecom

Thinking ModeTools

94.74

15 / 35

τ²-Bench

Thinking ModeTools

82.71

10 / 43

Instruction Following

1 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

Thinking ModeTools

31 / 33

Claw-style Agent Evaluation

2 evaluations

Benchmark / mode

Score

Rank/total

Claw Bench

Thinking ModeTools

88.60

12 / 29

Pinch Bench

Thinking ModeTools

82.40

21 / 38

Compare with other models