GLM-5 (Reasoning) vs Grok 3 [Beta]

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

Quick Verdict

GLM-5 (Reasoning) wins overall with a score of 75 vs 33 (42 point difference).GLM-5 (Reasoning) wins 4 out of 4 categories.

Knowledge

GLM-5 (Reasoning)

GLM-5 (Reasoning)

93

Grok 3 [Beta]

39.8

96
MMLU
42
94
GPQA
41
92
SuperGPQA
39
90
OpenBookQA
37

Coding

GLM-5 (Reasoning)

GLM-5 (Reasoning)

88

Grok 3 [Beta]

34

88
HumanEval
34

Mathematics

GLM-5 (Reasoning)

GLM-5 (Reasoning)

96.6

Grok 3 [Beta]

41

98
AIME 2023
42
99
AIME 2024
44
98
AIME 2025
43
94
HMMT Feb 2023
38
96
HMMT Feb 2024
40
95
HMMT Feb 2025
39
96
BRUMO 2025
41

Reasoning

GLM-5 (Reasoning)

GLM-5 (Reasoning)

91

Grok 3 [Beta]

39

92
SimpleQA
40
90
MuSR
38

Frequently Asked Questions

Which is better, GLM-5 (Reasoning) or Grok 3 [Beta]?

GLM-5 (Reasoning) scores higher overall with 75 vs 33, a difference of 42 points across all benchmarks.

Which is better for knowledge tasks, GLM-5 (Reasoning) or Grok 3 [Beta]?

GLM-5 (Reasoning) leads in knowledge tasks with an average score of 93 vs 39.8.

Which is better for coding, GLM-5 (Reasoning) or Grok 3 [Beta]?

GLM-5 (Reasoning) leads in coding with an average score of 88 vs 34.

Which is better for math, GLM-5 (Reasoning) or Grok 3 [Beta]?

GLM-5 (Reasoning) leads in math with an average score of 96.6 vs 41.

Which is better for reasoning, GLM-5 (Reasoning) or Grok 3 [Beta]?

GLM-5 (Reasoning) leads in reasoning with an average score of 91 vs 39.