Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeek V3.2 (Thinking) wins overall with a score of 69 vs 26 (43 point difference).DeepSeek V3.2 (Thinking) wins 4 out of 4 categories.
DeepSeek V3.2 (Thinking)
84
GLM-4.5-Air
32.8
DeepSeek V3.2 (Thinking)
79
GLM-4.5-Air
27
DeepSeek V3.2 (Thinking)
86
GLM-4.5-Air
34
DeepSeek V3.2 (Thinking)
82
GLM-4.5-Air
32
DeepSeek V3.2 (Thinking) scores higher overall with 69 vs 26, a difference of 43 points across all benchmarks.
DeepSeek V3.2 (Thinking) leads in knowledge tasks with an average score of 84 vs 32.8.
DeepSeek V3.2 (Thinking) leads in coding with an average score of 79 vs 27.
DeepSeek V3.2 (Thinking) leads in math with an average score of 86 vs 34.
DeepSeek V3.2 (Thinking) leads in reasoning with an average score of 82 vs 32.