GPT-4.1 Benchmark Details

GPT-4.1 currently shows benchmark results led by GSM8K (5 / 70, score 95.90), MMLU (9 / 124, score 90.20), DROP (4 / 9, score 89.20).

Benchmark Results

GPT-4.1

Benchmark Results

General Knowledge

3 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

90.20

9 / 124

MMLU Pro

Standard Mode

80.50

61 / 133

HLE

Standard Mode

3.70

184 / 185

Math and Reasoning

6 evaluations

Benchmark / mode

Score

Rank/total

GSM8K

Standard Mode

95.90

5 / 70

MATH-500

Standard Mode

92.80

30 / 44

AIME 2024

Standard Mode

48.10

49 / 62

AIME2025

Standard Mode

36.70

97 / 106

FrontierMath

Standard Mode

5.50

37 / 60

FrontierMath - Tier 4

Standard Mode

72 / 80

Reading Comprehension

1 evaluations

Benchmark / mode

Score

Rank/total

DROP

Standard Mode

89.20

4 / 9

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

66.30

208 / 270

Coding and Software Engineer

5 evaluations

Benchmark / mode

Score

Rank/total

SWE-bench Verified

Standard Mode

54.60

90 / 114

LiveCodeBench

Standard Mode

40.50

106 / 127

WeirdML v2

Standard ModeTools

39.04

48 / 52

SWE Manager Lancer(Diamond)

Standard Mode

35.10

1 / 1

IC SWE-Lancer(Diamond)

Standard Mode

14.40

8 / 8

Writing and Creative Capabilities

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

1417

56 / 99

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleBench

Standard Mode

56 / 67

Agent Level Benchmark

2 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench

Standard ModeTools

54.70

32 / 43

Aider-Polyglot

Standard Mode

52.40

31 / 59

Other

1 evaluations

Benchmark / mode

Score

Rank/total

Fiction.liveBench

Standard Mode

63.90

15 / 16

Multimodal Understanding

1 evaluations

Benchmark / mode

Score

Rank/total

GeoBench ACW

Standard Mode

12 / 20

Compare with other models