Qwen2.5-Max Benchmark Details

Qwen2.5-Max currently shows benchmark results led by GSM8K (9 / 70, score 94.50), MMLU (22 / 124, score 87.90), MBPP (19 / 96, score 80.60).

Benchmark Results

Qwen2.5-Max

Benchmark Results

General Knowledge

3 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

87.90

22 / 124

MMLU Pro

Standard Mode

76.10

82 / 176

HLE

Standard Mode

3.80

533 / 563

Math and Reasoning

3 evaluations

Benchmark / mode

Score

Rank/total

GSM8K

Standard Mode

94.50

9 / 70

MATH

Standard Mode

68.50

24 / 42

FrontierMath

Standard Mode

52 / 60

Coding and Software Engineer

3 evaluations

Benchmark / mode

Score

Rank/total

MBPP

Standard Mode

80.60

19 / 96

HumanEval

Standard Mode

73.20

51 / 140

LiveCodeBench

Standard Mode

35.90

194 / 250

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

58.70

384 / 462

Agent Level Benchmark

1 evaluations

Benchmark / mode

Score

Rank/total

Aider-Polyglot

Standard Mode

21.80

48 / 59

Compare with other models