GPT-4o Benchmark Details

GPT-4o currently shows benchmark results led by HumanEval (8 / 39, score 90), MMLU (15 / 65, score 88.70), BBH (5 / 20, score 91.70).

Benchmark Results

GPT-4o

Benchmark Results

综合评估

5 evaluations

Benchmark / mode

Score

Rank/total

BBH

Standard Mode

91.70

5 / 20

MMLU

Standard Mode

88.70

15 / 65

MMLU Pro

Standard Mode

77.90

72 / 126

GPQA Diamond

Standard Mode

70.10

112 / 177

HLE

Standard Mode

5.30

146 / 154

编程与软件工程

4 evaluations

Benchmark / mode

Score

Rank/total

HumanEval

Standard Mode

8 / 39

LiveCodeBench

Standard Mode

35.10

105 / 120

SWE-bench Verified

Standard Mode

100 / 105

IC SWE-Lancer(Diamond)

Standard Mode

23.30

6 / 8

数学推理

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

常识问答

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

38.20

20 / 45

OpenClaw智能体能力综合测评

1 evaluations

Benchmark / mode

Score

Rank/total

Pinch Bench

Thinking EnabledTools

71.10

30 / 37

Compare with other models

GPT-4o Benchmark Details

GPT-4o currently shows benchmark results led by HumanEval (8 / 39, score 90), MMLU (15 / 65, score 88.70), BBH (5 / 20, score 91.70).

Benchmark Results

GPT-4o

Benchmark Results

综合评估

5 evaluations

Benchmark / mode

Score

Rank/total

BBH

Standard Mode

91.70

5 / 20

MMLU

Standard Mode

88.70

15 / 65

MMLU Pro

Standard Mode

77.90

72 / 126

GPQA Diamond

Standard Mode

70.10

112 / 177

HLE

Standard Mode

5.30

146 / 154

编程与软件工程

4 evaluations

Benchmark / mode

Score

Rank/total

HumanEval

Standard Mode

8 / 39

LiveCodeBench

Standard Mode

35.10

105 / 120

SWE-bench Verified

Standard Mode

100 / 105

IC SWE-Lancer(Diamond)

Standard Mode

23.30

6 / 8

数学推理

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

常识问答

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

38.20

20 / 45

OpenClaw智能体能力综合测评

1 evaluations

Benchmark / mode

Score

Rank/total

Pinch Bench

Thinking EnabledTools

71.10

30 / 37

Compare with other models