GLM-4.5 Benchmark Details

GLM-4.5 currently shows benchmark results led by MATH-500 (4 / 46, score 98.20), MMLU-Pro (35 / 175, score 84.60), AIME 2024 (14 / 61, score 91).

Benchmark Results

GLM-4.5

Benchmark Results

Knowledge Exams

3 evaluations

Benchmark / mode

Score

Rank/total

Thinking Mode

84.60

35 / 175

unknown

8.32

206 / 235

Thinking Mode

14.40

179 / 235

Scientific Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Thinking Mode

79.10

136 / 253

Repository Engineering

1 evaluations

Benchmark / mode

Score

Rank/total

SWE-bench Verified

Thinking Mode

64.20

77 / 116

Mathematics

2 evaluations

Benchmark / mode

Score

Rank/total

Thinking Mode

98.20

4 / 46

Thinking Mode

91

14 / 61

Algorithmic Coding

1 evaluations

Benchmark / mode

Score

Rank/total

Thinking Mode

72.90

50 / 125

Writing

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

1343.30

74 / 110

Agentic Development

2 evaluations

Benchmark / mode

Score

Rank/total

Thinking Mode

37.50

15 / 35

Terminal Bench Hard

Thinking ModeTools

22

144 / 244

Compare with other models