Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GLM-4.7 wins overall with a score of 67 vs 64 (3 point difference).GLM-4.7 wins 4 out of 4 categories.
DeepSeekMath V2
77.8
GLM-4.7
83
DeepSeekMath V2
72
GLM-4.7
78
DeepSeekMath V2
79
GLM-4.7
85
DeepSeekMath V2
76
GLM-4.7
81
GLM-4.7 scores higher overall with 67 vs 64, a difference of 3 points across all benchmarks.
GLM-4.7 leads in knowledge tasks with an average score of 83 vs 77.8.
GLM-4.7 leads in coding with an average score of 78 vs 72.
GLM-4.7 leads in math with an average score of 85 vs 79.
GLM-4.7 leads in reasoning with an average score of 81 vs 76.