Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeek V3.2 (Thinking) wins overall with a score of 69 vs 54 (15 point difference).DeepSeek V3.2 (Thinking) wins 4 out of 4 categories.
DeepSeek V3.2 (Thinking)
84
Gemini 1.5 Pro
62.5
DeepSeek V3.2 (Thinking)
79
Gemini 1.5 Pro
56
DeepSeek V3.2 (Thinking)
86
Gemini 1.5 Pro
63
DeepSeek V3.2 (Thinking)
82
Gemini 1.5 Pro
61
DeepSeek V3.2 (Thinking) scores higher overall with 69 vs 54, a difference of 15 points across all benchmarks.
DeepSeek V3.2 (Thinking) leads in knowledge tasks with an average score of 84 vs 62.5.
DeepSeek V3.2 (Thinking) leads in coding with an average score of 79 vs 56.
DeepSeek V3.2 (Thinking) leads in math with an average score of 86 vs 63.
DeepSeek V3.2 (Thinking) leads in reasoning with an average score of 82 vs 61.