Qwen2.5-7B Benchmark Details

Qwen2.5-7B currently shows benchmark results led by MBPP (27 / 96, score 74.90), GSM8K (21 / 71, score 85.40), ARC (2 / 4, score 63.70).

Benchmark Results

Qwen2.5-7B

Benchmark Results

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

74.20

67 / 124

MMLU-Pro

Standard Mode

147 / 176

Math and Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

GSM8K

Standard Mode

85.40

21 / 71

MATH

Standard Mode

49.80

34 / 42

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

MBPP

Standard Mode

74.90

27 / 96

HumanEval

Standard Mode

57.90

76 / 140

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

ARC

Standard Mode

63.70

2 / 4

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

36.40

439 / 463

Claw-style Agent Evaluation

1 evaluations

Benchmark / mode

Score

Rank/total

Pinch Bench

Thinking EnabledTools

40.30

38 / 38

Compare with other models