benchlm.ai

GLM-4.5-Air vs GLM-5 (Reasoning)

Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.

Quick Verdict

GLM-5 (Reasoning) wins overall with a score of 75 vs 26 (49 point difference).GLM-5 (Reasoning) wins 4 out of 4 categories.

GLM-4.5-Air

CreatorTsinghua
TypeProprietary
Context128K
Score26

GLM-5 (Reasoning)

CreatorZhipu AI
TypeOpen Weight
Context200K
Score75

Knowledge

GLM-5 (Reasoning)

GLM-4.5-Air

32.8

GLM-5 (Reasoning)

93

35
MMLU
96
34
GPQA
94
32
SuperGPQA
92
30
OpenBookQA
90

Coding

GLM-5 (Reasoning)

GLM-4.5-Air

27

GLM-5 (Reasoning)

88

27
HumanEval
88

Mathematics

GLM-5 (Reasoning)

GLM-4.5-Air

34

GLM-5 (Reasoning)

96.6

35
AIME 2023
98
37
AIME 2024
99
36
AIME 2025
98
31
HMMT Feb 2023
94
33
HMMT Feb 2024
96
32
HMMT Feb 2025
95
34
BRUMO 2025
96

Reasoning

GLM-5 (Reasoning)

GLM-4.5-Air

32

GLM-5 (Reasoning)

91

33
SimpleQA
92
31
MuSR
90

Frequently Asked Questions

Which is better, GLM-4.5-Air or GLM-5 (Reasoning)?

GLM-5 (Reasoning) scores higher overall with 75 vs 26, a difference of 49 points across all benchmarks.

Which is better for knowledge tasks, GLM-4.5-Air or GLM-5 (Reasoning)?

GLM-5 (Reasoning) leads in knowledge tasks with an average score of 93 vs 32.8.

Which is better for coding, GLM-4.5-Air or GLM-5 (Reasoning)?

GLM-5 (Reasoning) leads in coding with an average score of 88 vs 27.

Which is better for math, GLM-4.5-Air or GLM-5 (Reasoning)?

GLM-5 (Reasoning) leads in math with an average score of 96.6 vs 34.

Which is better for reasoning, GLM-4.5-Air or GLM-5 (Reasoning)?

GLM-5 (Reasoning) leads in reasoning with an average score of 91 vs 32.

Related Comparisons

GLM-4.5-Air vs GPT-5.4GLM-4.5-Air vs Gemini 3.1 ProGLM-4.5-Air vs Claude Opus 4.6GLM-4.5-Air vs GPT-5.3 CodexGLM-4.5-Air vs Grok 4.1GLM-4.5-Air vs GPT-5.2