DeepSeek-V3-0324 Benchmark Details

DeepSeek-V3-0324 currently shows benchmark results led by GSM8K (3 / 70, score 96.30), MMLU (29 / 124, score 86.50), GPQA (4 / 17, score 68.40).

Benchmark Results

DeepSeek-V3-0324

Benchmark Results

General Knowledge

5 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

86.50

29 / 124

MMLU Pro

Standard Mode

81.20

56 / 134

GPQA

Standard Mode

68.40

4 / 17

ARC-AGI-1

Standard Mode

86 / 92

HLE

Standard Mode

5.20

190 / 197

Math and Reasoning

7 evaluations

Benchmark / mode

Score

Rank/total

GSM8K

Standard Mode

96.30

3 / 70

MATH-500

Standard Mode

29 / 45

AIME 2024

Standard Mode

59.40

43 / 62

AIME2025

Standard Mode

47.70

89 / 107

IMO-ProofBench

Standard Mode

4.30

15 / 16

IMO 2024

Standard Mode

1.70

9 / 10

IMO 2025

Standard Mode

1.70

9 / 9

Reading Comprehension

1 evaluations

Benchmark / mode

Score

Rank/total

DROP

Standard Mode

89.70

3 / 9

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

68.40

205 / 274

Common Sense

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

27.20

28 / 47

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Standard Mode

49.20

100 / 128

SWE-bench Verified

Standard Mode

38.80

107 / 116

Writing and Creative Capabilities

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

1470.20

55 / 106

AI Agent - Tool Usage

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal-Bench

Standard Mode

13.30

34 / 35

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleBench

Standard Mode

27.20

79 / 94

Agent Level Benchmark

2 evaluations

Benchmark / mode

Score

Rank/total

Aider-Polyglot

Standard Mode

55.10

27 / 59

τ²-Bench

Standard ModeTools

38.80

39 / 44

Compare with other models