benchlm.ai

GLM-4.5-Air vs GLM-4.7-Flash

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

Quick Verdict

GLM-4.7-Flash wins overall with a score of 56 vs 26 (30 point difference).GLM-4.7-Flash wins 4 out of 4 categories.

GLM-4.5-Air

CreatorTsinghua
TypeProprietary
Context128K
Score26

GLM-4.7-Flash

CreatorZhipu AI
TypeOpen Weight
Context200K
Score56

Knowledge

GLM-4.7-Flash

GLM-4.5-Air

32.8

GLM-4.7-Flash

63.8

35
MMLU
66
34
GPQA
65
32
SuperGPQA
63
30
OpenBookQA
61

Coding

GLM-4.7-Flash

GLM-4.5-Air

27

GLM-4.7-Flash

58

27
HumanEval
58

Mathematics

GLM-4.7-Flash

GLM-4.5-Air

34

GLM-4.7-Flash

65

35
AIME 2023
66
37
AIME 2024
68
36
AIME 2025
67
31
HMMT Feb 2023
62
33
HMMT Feb 2024
64
32
HMMT Feb 2025
63
34
BRUMO 2025
65

Reasoning

GLM-4.7-Flash

GLM-4.5-Air

32

GLM-4.7-Flash

62

33
SimpleQA
63
31
MuSR
61

Frequently Asked Questions

Which is better, GLM-4.5-Air or GLM-4.7-Flash?

GLM-4.7-Flash scores higher overall with 56 vs 26, a difference of 30 points across all benchmarks.

Which is better for knowledge tasks, GLM-4.5-Air or GLM-4.7-Flash?

GLM-4.7-Flash leads in knowledge tasks with an average score of 63.8 vs 32.8.

Which is better for coding, GLM-4.5-Air or GLM-4.7-Flash?

GLM-4.7-Flash leads in coding with an average score of 58 vs 27.

Which is better for math, GLM-4.5-Air or GLM-4.7-Flash?

GLM-4.7-Flash leads in math with an average score of 65 vs 34.

Which is better for reasoning, GLM-4.5-Air or GLM-4.7-Flash?

GLM-4.7-Flash leads in reasoning with an average score of 62 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