GPT-4.5 Benchmark Details

GPT-4.5 currently shows benchmark results led by MMLU Pro (19 / 132, score 86.10), SimpleQA (9 / 47, score 62.50), GPQA Diamond (111 / 187, score 71.40).

Benchmark Results

GPT-4.5

Benchmark Results

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

MMLU Pro

86.10

19 / 132

GPQA Diamond

71.40

111 / 187

Common Sense

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

62.50

9 / 47

Coding and Software Engineer

3 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

46.40

97 / 123

SWE-bench Verified

104 / 112

IC SWE-Lancer(Diamond)

32.60

5 / 8

Math and Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

MATH-500

90.70

34 / 44

AIME 2024

36.70

53 / 62

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Simple Bench

Standard Mode

34.50

46 / 63

Agent Level Benchmark

1 evaluations

Benchmark / mode

Score

Rank/total

Aider-Polyglot

Standard Mode

44.90

37 / 59

Compare with other models