GPT-5-Pro Benchmark Details

GPT-5-Pro currently shows benchmark results led by AIME2025 (1 / 106, score 100), LiveBench (3 / 52, score 78.73), GPQA Diamond (22 / 177, score 89.40).

Benchmark Results

GPT-5-Pro

Benchmark Results

综合评估

7 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Thinking Enabled

88.40

25 / 177

GPQA Diamond

Thinking EnabledTools

89.40

22 / 177

LiveBench

Thinking Enabled

78.73

3 / 52

ARC-AGI

Thinking Enabled

70.20

27 / 65

HLE

Thinking Enabled

30.70

68 / 154

HLE

Thinking EnabledTools

42 / 154

ARC-AGI-2

Thinking Enabled

32 / 59

数学推理

4 evaluations

Benchmark / mode

Score

Rank/total

AIME2025

Thinking Enabled

96.70

19 / 106

AIME2025

Thinking EnabledTools

100

1 / 106

FrontierMath - Tier 4

Standard Mode

14.60

23 / 80

FrontierMath - Tier 4

Thinking Enabled

14.60

23 / 80

常识推理

1 evaluations

Benchmark / mode

Score

Rank/total

Simple Bench

Thinking Enabled

61.60

4 / 27

Compare with other models

GPT-5-Pro Benchmark Details

GPT-5-Pro currently shows benchmark results led by AIME2025 (1 / 106, score 100), LiveBench (3 / 52, score 78.73), GPQA Diamond (22 / 177, score 89.40).