Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GLM-5 wins overall with a score of 68 vs 25 (43 point difference).GLM-5 wins 4 out of 4 categories.
DeepSeek V3.1 (Reasoning)
31.8
GLM-5
85
DeepSeek V3.1 (Reasoning)
26
GLM-5
80
DeepSeek V3.1 (Reasoning)
33
GLM-5
87
DeepSeek V3.1 (Reasoning)
31
GLM-5
83
GLM-5 scores higher overall with 68 vs 25, a difference of 43 points across all benchmarks.
GLM-5 leads in knowledge tasks with an average score of 85 vs 31.8.
GLM-5 leads in coding with an average score of 80 vs 26.
GLM-5 leads in math with an average score of 87 vs 33.
GLM-5 leads in reasoning with an average score of 83 vs 31.