Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeek V3.2 (Thinking) wins overall with a score of 69 vs 27 (42 point difference).DeepSeek V3.2 (Thinking) wins 4 out of 4 categories.
DeepSeek V3.2 (Thinking)
84
MiniMax M1 80k
33.8
DeepSeek V3.2 (Thinking)
79
MiniMax M1 80k
28
DeepSeek V3.2 (Thinking)
86
MiniMax M1 80k
35
DeepSeek V3.2 (Thinking)
82
MiniMax M1 80k
33
DeepSeek V3.2 (Thinking) scores higher overall with 69 vs 27, a difference of 42 points across all benchmarks.
DeepSeek V3.2 (Thinking) leads in knowledge tasks with an average score of 84 vs 33.8.
DeepSeek V3.2 (Thinking) leads in coding with an average score of 79 vs 28.
DeepSeek V3.2 (Thinking) leads in math with an average score of 86 vs 35.
DeepSeek V3.2 (Thinking) leads in reasoning with an average score of 82 vs 33.