GPT-5-Nano Benchmark Details

GPT-5-Nano currently shows benchmark results led by FrontierMath (31 / 60, score 8.30), FrontierMath - Tier 4 (56 / 80, score 2.10), LiveBench (46 / 52, score 59).

Benchmark Results

GPT-5-Nano

Benchmark Results

多模态理解

2 evaluations

Benchmark / mode

Score

Rank/total

DocVQA

Standard Mode

78.30

5 / 5

MMMU

Standard Mode

57.60

28 / 28

数学推理

4 evaluations

Benchmark / mode

Score

Rank/total

FrontierMath

Thinking Level · Medium

7.20

33 / 60

FrontierMath

Thinking Level · High

8.30

31 / 60

FrontierMath - Tier 4

Thinking Level · Medium

2.10

56 / 80

FrontierMath - Tier 4

Thinking Level · High

72 / 80

综合评估

1 evaluations

Benchmark / mode

Score

Rank/total

LiveBench

Standard Mode

46 / 52

OpenClaw智能体能力综合测评

1 evaluations

Benchmark / mode

Score

Rank/total

Pinch Bench

Thinking EnabledTools

68.80

33 / 37

Compare with other models