Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeekMath V2 wins overall with a score of 64 vs 59 (5 point difference).DeepSeekMath V2 wins 4 out of 4 categories.
Claude 4 Sonnet
71.5
DeepSeekMath V2
77.8
Claude 4 Sonnet
65
DeepSeekMath V2
72
Claude 4 Sonnet
72
DeepSeekMath V2
79
Claude 4 Sonnet
70
DeepSeekMath V2
76
DeepSeekMath V2 scores higher overall with 64 vs 59, a difference of 5 points across all benchmarks.
DeepSeekMath V2 leads in knowledge tasks with an average score of 77.8 vs 71.5.
DeepSeekMath V2 leads in coding with an average score of 72 vs 65.
DeepSeekMath V2 leads in math with an average score of 79 vs 72.
DeepSeekMath V2 leads in reasoning with an average score of 76 vs 70.