GPT-4o(2025-03-27) Benchmark Details

GPT-4o(2025-03-27) currently shows benchmark results led by MMLU Pro (66 / 176, score 79.80), SimpleQA (20 / 47, score 40.30), Creative Writing (50 / 106, score 1502.10).

Benchmark Results

GPT-4o(2025-03-27)

Benchmark Results

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

MMLU Pro

Standard Mode

79.80

66 / 176

ARC-AGI-1

Standard Mode

8.80

141 / 147

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

66.90

346 / 462

Common Sense

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

40.30

20 / 47

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Standard Mode

35.80

195 / 250

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

AIME2025

Standard Mode

26.70

189 / 215

Writing and Creative Capabilities

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

1502.10

50 / 106

Agent Level Benchmark

1 evaluations

Benchmark / mode

Score

Rank/total

Aider-Polyglot

Standard Mode

45.30

36 / 59

Compare with other models