GLM-4.5-Air Benchmark Details

GLM-4.5-Air currently shows benchmark results led by MATH-500 (5 / 44, score 98.10), AIME 2024 (15 / 62, score 89.40), Pinch Bench (14 / 38, score 85.70).

Benchmark Results

GLM-4.5-Air

Benchmark Results

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

MMLU Pro

Thinking Mode

81.40

55 / 133

HLE

Thinking Mode

10.60

158 / 185

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Thinking Mode

171 / 270

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Thinking Mode

70.70

53 / 127

SWE-bench Verified

Thinking Mode

57.60

86 / 114

Math and Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

MATH-500

Thinking Mode

98.10

5 / 44

AIME 2024

Thinking Mode

89.40

15 / 62

AI Agent - Tool Usage

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal-Bench

Thinking Mode

22 / 35

Claw-style Agent Evaluation

1 evaluations

Benchmark / mode

Score

Rank/total

Pinch Bench

Thinking ModeTools

85.70

14 / 38

Compare with other models