DeepSeek V3.1 vs GLM-4.5

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

Quick Verdict

GLM-4.5 wins overall with a score of 28 vs 24 (4 point difference).GLM-4.5 wins 4 out of 4 categories.

Knowledge

GLM-4.5

DeepSeek V3.1

30.8

GLM-4.5

34.8

33
MMLU
37
32
GPQA
36
30
SuperGPQA
34
28
OpenBookQA
32

Coding

GLM-4.5

DeepSeek V3.1

25

GLM-4.5

29

25
HumanEval
29

Mathematics

GLM-4.5

DeepSeek V3.1

32

GLM-4.5

36

33
AIME 2023
37
35
AIME 2024
39
34
AIME 2025
38
29
HMMT Feb 2023
33
31
HMMT Feb 2024
35
30
HMMT Feb 2025
34
32
BRUMO 2025
36

Reasoning

GLM-4.5

DeepSeek V3.1

30

GLM-4.5

34

31
SimpleQA
35
29
MuSR
33

Frequently Asked Questions

Which is better, DeepSeek V3.1 or GLM-4.5?

GLM-4.5 scores higher overall with 28 vs 24, a difference of 4 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.1 or GLM-4.5?

GLM-4.5 leads in knowledge tasks with an average score of 34.8 vs 30.8.

Which is better for coding, DeepSeek V3.1 or GLM-4.5?

GLM-4.5 leads in coding with an average score of 29 vs 25.

Which is better for math, DeepSeek V3.1 or GLM-4.5?

GLM-4.5 leads in math with an average score of 36 vs 32.

Which is better for reasoning, DeepSeek V3.1 or GLM-4.5?

GLM-4.5 leads in reasoning with an average score of 34 vs 30.