DeepSeek-V3 Benchmark Details

DeepSeek-V3 currently shows benchmark results led by BBH (3 / 20, score 92.30), MATH (7 / 42, score 87.80), HumanEval (9 / 39, score 89).

Benchmark Results

DeepSeek-V3

Benchmark Results

综合评估

5 evaluations

Benchmark / mode

Score

Rank/total

BBH

Standard Mode

92.30

3 / 20

MMLU

Standard Mode

88.50

17 / 65

MMLU Pro

Standard Mode

75.90

78 / 124

GPQA Diamond

Standard Mode

59.10

139 / 175

GPQA

Standard Mode

59.10

5 / 14

编程与软件工程

2 evaluations

Benchmark / mode

Score

Rank/total

HumanEval

Standard Mode

9 / 39

LiveCodeBench

Standard Mode

34.60

105 / 118

数学推理

4 evaluations

Benchmark / mode

Score

Rank/total

MATH

Standard Mode

87.80

7 / 42

MATH-500

Standard Mode

87.80

39 / 44

AIME 2024

Standard Mode

52 / 62

FrontierMath

Standard Mode

1.70

49 / 60

常识问答

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

24.90

29 / 45

写作和创作

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

81.60

15 / 23

常识推理

1 evaluations

Benchmark / mode

Score

Rank/total

Simple Bench

Standard Mode

18.90

27 / 27

Compare with other models

DeepSeek-V3 Benchmark Details

DeepSeek-V3 currently shows benchmark results led by BBH (3 / 20, score 92.30), MATH (7 / 42, score 87.80), HumanEval (9 / 39, score 89).

Benchmark Results

DeepSeek-V3

Benchmark Results

综合评估

5 evaluations

Benchmark / mode

Score

Rank/total

BBH

Standard Mode

92.30

3 / 20

MMLU

Standard Mode

88.50

17 / 65

MMLU Pro

Standard Mode

75.90

78 / 124

GPQA Diamond

Standard Mode

59.10

139 / 175

GPQA

Standard Mode

59.10

5 / 14

编程与软件工程

2 evaluations

Benchmark / mode

Score

Rank/total

HumanEval

Standard Mode

9 / 39

LiveCodeBench

Standard Mode

34.60

105 / 118

数学推理

4 evaluations

Benchmark / mode

Score

Rank/total

MATH

Standard Mode

87.80

7 / 42

MATH-500

Standard Mode

87.80

39 / 44

AIME 2024

Standard Mode

52 / 62

FrontierMath

Standard Mode

1.70

49 / 60

常识问答

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

24.90

29 / 45

写作和创作

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

81.60

15 / 23

常识推理

1 evaluations

Benchmark / mode

Score

Rank/total

Simple Bench

Standard Mode

18.90

27 / 27

Compare with other models