Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeekMath V2 wins overall with a score of 64 vs 44 (20 point difference).DeepSeekMath V2 wins 4 out of 4 categories.
DeepSeekMath V2
77.8
Moonshot v1
50.8
DeepSeekMath V2
72
Moonshot v1
45
DeepSeekMath V2
79
Moonshot v1
52
DeepSeekMath V2
76
Moonshot v1
50
DeepSeekMath V2 scores higher overall with 64 vs 44, a difference of 20 points across all benchmarks.
DeepSeekMath V2 leads in knowledge tasks with an average score of 77.8 vs 50.8.
DeepSeekMath V2 leads in coding with an average score of 72 vs 45.
DeepSeekMath V2 leads in math with an average score of 79 vs 52.
DeepSeekMath V2 leads in reasoning with an average score of 76 vs 50.