GPT-4.1 Benchmark Details

GPT-4.1 currently shows benchmark results led by MMLU (9 / 66, score 90.20), GSM8K (5 / 26, score 95.90), DROP (4 / 9, score 89.20).

Benchmark Results

GPT-4.1

Benchmark Results

General Knowledge

4 evaluations

Benchmark / mode

Score

Rank/total

MMLU

90.20

9 / 66

MMLU Pro

80.50

60 / 132

GPQA Diamond

66.30

132 / 187

HLE

3.70

169 / 170

Math and Reasoning

6 evaluations

Benchmark / mode

Score

Rank/total

GSM8K

95.90

5 / 26

MATH-500

92.80

30 / 44

AIME 2024

48.10

49 / 62

AIME2025

36.70

98 / 107

FrontierMath

5.50

37 / 60

FrontierMath - Tier 4

Standard Mode

72 / 80

Reading Comprehension

1 evaluations

Benchmark / mode

Score

Rank/total

DROP

89.20

4 / 9

Coding and Software Engineer

4 evaluations

Benchmark / mode

Score

Rank/total

SWE-bench Verified

54.60

87 / 111

LiveCodeBench

40.50

102 / 123

SWE Manager Lancer(Diamond)

35.10

1 / 1

IC SWE-Lancer(Diamond)

14.40

8 / 8

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Simple Bench

Standard Mode

52 / 63

Agent Level Benchmark

2 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench

54.70

32 / 43

Aider-Polyglot

Standard Mode

52.40

31 / 59

Compare with other models