GPT-4o Benchmark Details

GPT-4o currently shows benchmark results led by HumanEval (8 / 101, score 90), MMLU (16 / 124, score 88.70), BBH (5 / 21, score 91.70).

Benchmark Results

GPT-4o

Benchmark Results

General Knowledge

4 evaluations

Benchmark / mode

Score

Rank/total

BBH

Standard Mode

91.70

5 / 21

MMLU

Standard Mode

88.70

16 / 124

MMLU Pro

Standard Mode

77.90

76 / 133

HLE

Standard Mode

5.30

177 / 185

Coding and Software Engineer

4 evaluations

Benchmark / mode

Score

Rank/total

HumanEval

Standard Mode

8 / 101

LiveCodeBench

Standard Mode

35.10

112 / 127

SWE-bench Verified

Standard Mode

109 / 114

IC SWE-Lancer(Diamond)

Standard Mode

23.30

6 / 8

Math and Reasoning

5 evaluations

Benchmark / mode

Score

Rank/total

MATH

Standard Mode

75.90

16 / 42

MATH-500

Standard Mode

75.90

43 / 44

AIME2025

Standard ModeTools

42.10

93 / 106

AIME 2024

Standard Mode

9.30

61 / 62

FrontierMath

Standard Mode

0.30

57 / 60

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

70.10

195 / 270

Common Sense

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

38.20

22 / 47

Agent Level Benchmark

1 evaluations

Benchmark / mode

Score

Rank/total

Aider-Polyglot

Standard Mode

23.10

47 / 59

Claw-style Agent Evaluation

1 evaluations

Benchmark / mode

Score

Rank/total

Pinch Bench

Thinking ModeTools

71.10

31 / 38

Compare with other models