Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeek-R1 wins overall with a score of 35 vs 26 (9 point difference).DeepSeek-R1 wins 4 out of 4 categories.
DeepSeek-R1
41.8
GLM-4.5-Air
32.8
DeepSeek-R1
36
GLM-4.5-Air
27
DeepSeek-R1
43
GLM-4.5-Air
34
DeepSeek-R1
41
GLM-4.5-Air
32
DeepSeek-R1 scores higher overall with 35 vs 26, a difference of 9 points across all benchmarks.
DeepSeek-R1 leads in knowledge tasks with an average score of 41.8 vs 32.8.
DeepSeek-R1 leads in coding with an average score of 36 vs 27.
DeepSeek-R1 leads in math with an average score of 43 vs 34.
DeepSeek-R1 leads in reasoning with an average score of 41 vs 32.