Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeek V3.2 (Thinking) wins overall with a score of 69 vs 59 (10 point difference).DeepSeek V3.2 (Thinking) wins 4 out of 4 categories.
Claude 4 Sonnet
71.5
DeepSeek V3.2 (Thinking)
84
Claude 4 Sonnet
65
DeepSeek V3.2 (Thinking)
79
Claude 4 Sonnet
72
DeepSeek V3.2 (Thinking)
86
Claude 4 Sonnet
70
DeepSeek V3.2 (Thinking)
82
DeepSeek V3.2 (Thinking) scores higher overall with 69 vs 59, a difference of 10 points across all benchmarks.
DeepSeek V3.2 (Thinking) leads in knowledge tasks with an average score of 84 vs 71.5.
DeepSeek V3.2 (Thinking) leads in coding with an average score of 79 vs 65.
DeepSeek V3.2 (Thinking) leads in math with an average score of 86 vs 72.
DeepSeek V3.2 (Thinking) leads in reasoning with an average score of 82 vs 70.