Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeek V3.2 (Thinking) wins overall with a score of 69 vs 67 (2 point difference).DeepSeek V3.2 (Thinking) wins 1 out of 4 categories.
DeepSeek V3.2 (Thinking)
84
o3
85.3
DeepSeek V3.2 (Thinking)
79
o3
78
DeepSeek V3.2 (Thinking)
86
o3
87
DeepSeek V3.2 (Thinking)
82
o3
83
DeepSeek V3.2 (Thinking) scores higher overall with 69 vs 67, a difference of 2 points across all benchmarks.
o3 leads in knowledge tasks with an average score of 85.3 vs 84.
DeepSeek V3.2 (Thinking) leads in coding with an average score of 79 vs 78.
o3 leads in math with an average score of 87 vs 86.
o3 leads in reasoning with an average score of 83 vs 82.