benchlm.ai

GLM-4.5 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 28 (47 point difference).GLM-5 (Reasoning) wins 4 out of 4 categories.

GLM-4.5

CreatorTsinghua
TypeProprietary
Context128K
Score28

GLM-5 (Reasoning)

CreatorZhipu AI
TypeOpen Weight
Context200K
Score75

Knowledge

GLM-5 (Reasoning)

GLM-4.5

34.8

GLM-5 (Reasoning)

93

37
MMLU
96
36
GPQA
94
34
SuperGPQA
92
32
OpenBookQA
90

Coding

GLM-5 (Reasoning)

GLM-4.5

29

GLM-5 (Reasoning)

88

29
HumanEval
88

Mathematics

GLM-5 (Reasoning)

GLM-4.5

36

GLM-5 (Reasoning)

96.6

37
AIME 2023
98
39
AIME 2024
99
38
AIME 2025
98
33
HMMT Feb 2023
94
35
HMMT Feb 2024
96
34
HMMT Feb 2025
95
36
BRUMO 2025
96

Reasoning

GLM-5 (Reasoning)

GLM-4.5

34

GLM-5 (Reasoning)

91

35
SimpleQA
92
33
MuSR
90

Frequently Asked Questions

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

GLM-5 (Reasoning) scores higher overall with 75 vs 28, a difference of 47 points across all benchmarks.

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

GLM-5 (Reasoning) leads in knowledge tasks with an average score of 93 vs 34.8.

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

GLM-5 (Reasoning) leads in coding with an average score of 88 vs 29.

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

GLM-5 (Reasoning) leads in math with an average score of 96.6 vs 36.

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

GLM-5 (Reasoning) leads in reasoning with an average score of 91 vs 34.

Related Comparisons

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