benchlm.ai

DeepSeek V3.1 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 24 (51 point difference).GLM-5 (Reasoning) wins 4 out of 4 categories.

DeepSeek V3.1

CreatorDeepSeek
TypeOpen Weight
Context128K
Score24

GLM-5 (Reasoning)

CreatorZhipu AI
TypeOpen Weight
Context200K
Score75

Knowledge

GLM-5 (Reasoning)

DeepSeek V3.1

30.8

GLM-5 (Reasoning)

93

33
MMLU
96
32
GPQA
94
30
SuperGPQA
92
28
OpenBookQA
90

Coding

GLM-5 (Reasoning)

DeepSeek V3.1

25

GLM-5 (Reasoning)

88

25
HumanEval
88

Mathematics

GLM-5 (Reasoning)

DeepSeek V3.1

32

GLM-5 (Reasoning)

96.6

33
AIME 2023
98
35
AIME 2024
99
34
AIME 2025
98
29
HMMT Feb 2023
94
31
HMMT Feb 2024
96
30
HMMT Feb 2025
95
32
BRUMO 2025
96

Reasoning

GLM-5 (Reasoning)

DeepSeek V3.1

30

GLM-5 (Reasoning)

91

31
SimpleQA
92
29
MuSR
90

Frequently Asked Questions

Which is better, DeepSeek V3.1 or GLM-5 (Reasoning)?

GLM-5 (Reasoning) scores higher overall with 75 vs 24, a difference of 51 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.1 or GLM-5 (Reasoning)?

GLM-5 (Reasoning) leads in knowledge tasks with an average score of 93 vs 30.8.

Which is better for coding, DeepSeek V3.1 or GLM-5 (Reasoning)?

GLM-5 (Reasoning) leads in coding with an average score of 88 vs 25.

Which is better for math, DeepSeek V3.1 or GLM-5 (Reasoning)?

GLM-5 (Reasoning) leads in math with an average score of 96.6 vs 32.

Which is better for reasoning, DeepSeek V3.1 or GLM-5 (Reasoning)?

GLM-5 (Reasoning) leads in reasoning with an average score of 91 vs 30.

Related Comparisons

DeepSeek V3.1 vs GPT-5.4DeepSeek V3.1 vs Gemini 3.1 ProDeepSeek V3.1 vs Claude Opus 4.6DeepSeek V3.1 vs GPT-5.3 CodexDeepSeek V3.1 vs Grok 4.1DeepSeek V3.1 vs GPT-5.2