DeepSeek-R1 vs GLM-4.5-Air

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

Quick Verdict

DeepSeek-R1 wins overall with a score of 35 vs 26 (9 point difference).DeepSeek-R1 wins 4 out of 4 categories.

Knowledge

DeepSeek-R1

DeepSeek-R1

41.8

GLM-4.5-Air

32.8

44
MMLU
35
43
GPQA
34
41
SuperGPQA
32
39
OpenBookQA
30

Coding

DeepSeek-R1

DeepSeek-R1

36

GLM-4.5-Air

27

36
HumanEval
27

Mathematics

DeepSeek-R1

DeepSeek-R1

43

GLM-4.5-Air

34

44
AIME 2023
35
46
AIME 2024
37
45
AIME 2025
36
40
HMMT Feb 2023
31
42
HMMT Feb 2024
33
41
HMMT Feb 2025
32
43
BRUMO 2025
34

Reasoning

DeepSeek-R1

DeepSeek-R1

41

GLM-4.5-Air

32

42
SimpleQA
33
40
MuSR
31

Frequently Asked Questions

Which is better, DeepSeek-R1 or GLM-4.5-Air?

DeepSeek-R1 scores higher overall with 35 vs 26, a difference of 9 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek-R1 or GLM-4.5-Air?

DeepSeek-R1 leads in knowledge tasks with an average score of 41.8 vs 32.8.

Which is better for coding, DeepSeek-R1 or GLM-4.5-Air?

DeepSeek-R1 leads in coding with an average score of 36 vs 27.

Which is better for math, DeepSeek-R1 or GLM-4.5-Air?

DeepSeek-R1 leads in math with an average score of 43 vs 34.

Which is better for reasoning, DeepSeek-R1 or GLM-4.5-Air?

DeepSeek-R1 leads in reasoning with an average score of 41 vs 32.