Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeekMath V2 wins overall with a score of 64 vs 34 (30 point difference).DeepSeekMath V2 wins 4 out of 4 categories.
DeepSeekMath V2
77.8
Qwen2.5-VL-32B
40.8
DeepSeekMath V2
72
Qwen2.5-VL-32B
35
DeepSeekMath V2
79
Qwen2.5-VL-32B
42
DeepSeekMath V2
76
Qwen2.5-VL-32B
40
DeepSeekMath V2 scores higher overall with 64 vs 34, a difference of 30 points across all benchmarks.
DeepSeekMath V2 leads in knowledge tasks with an average score of 77.8 vs 40.8.
DeepSeekMath V2 leads in coding with an average score of 72 vs 35.
DeepSeekMath V2 leads in math with an average score of 79 vs 42.
DeepSeekMath V2 leads in reasoning with an average score of 76 vs 40.