benchlm.ai

Claude 3.5 Sonnet vs GLM-4.5-Air

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

Quick Verdict

Claude 3.5 Sonnet wins overall with a score of 55 vs 26 (29 point difference).Claude 3.5 Sonnet wins 4 out of 4 categories.

Claude 3.5 Sonnet

CreatorAnthropic
TypeProprietary
Context200K
Score55

GLM-4.5-Air

CreatorTsinghua
TypeProprietary
Context128K
Score26

Knowledge

Claude 3.5 Sonnet

Claude 3.5 Sonnet

63.5

GLM-4.5-Air

32.8

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

Coding

Claude 3.5 Sonnet

Claude 3.5 Sonnet

57

GLM-4.5-Air

27

57
HumanEval
27

Mathematics

Claude 3.5 Sonnet

Claude 3.5 Sonnet

64

GLM-4.5-Air

34

65
AIME 2023
35
67
AIME 2024
37
66
AIME 2025
36
61
HMMT Feb 2023
31
63
HMMT Feb 2024
33
62
HMMT Feb 2025
32
64
BRUMO 2025
34

Reasoning

Claude 3.5 Sonnet

Claude 3.5 Sonnet

62

GLM-4.5-Air

32

63
SimpleQA
33
61
MuSR
31

Frequently Asked Questions

Which is better, Claude 3.5 Sonnet or GLM-4.5-Air?

Claude 3.5 Sonnet scores higher overall with 55 vs 26, a difference of 29 points across all benchmarks.

Which is better for knowledge tasks, Claude 3.5 Sonnet or GLM-4.5-Air?

Claude 3.5 Sonnet leads in knowledge tasks with an average score of 63.5 vs 32.8.

Which is better for coding, Claude 3.5 Sonnet or GLM-4.5-Air?

Claude 3.5 Sonnet leads in coding with an average score of 57 vs 27.

Which is better for math, Claude 3.5 Sonnet or GLM-4.5-Air?

Claude 3.5 Sonnet leads in math with an average score of 64 vs 34.

Which is better for reasoning, Claude 3.5 Sonnet or GLM-4.5-Air?

Claude 3.5 Sonnet leads in reasoning with an average score of 62 vs 32.

Related Comparisons

Claude 3.5 Sonnet vs GPT-5.4Claude 3.5 Sonnet vs Gemini 3.1 ProClaude 3.5 Sonnet vs Claude Opus 4.6Claude 3.5 Sonnet vs GPT-5.3 CodexClaude 3.5 Sonnet vs Grok 4.1Claude 3.5 Sonnet vs GPT-5.2