Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeekMath V2 wins overall with a score of 64 vs 51 (13 point difference).DeepSeekMath V2 wins 4 out of 4 categories.
Claude 3 Opus
59.5
DeepSeekMath V2
77.8
Claude 3 Opus
53
DeepSeekMath V2
72
Claude 3 Opus
60
DeepSeekMath V2
79
Claude 3 Opus
58
DeepSeekMath V2
76
DeepSeekMath V2 scores higher overall with 64 vs 51, a difference of 13 points across all benchmarks.
DeepSeekMath V2 leads in knowledge tasks with an average score of 77.8 vs 59.5.
DeepSeekMath V2 leads in coding with an average score of 72 vs 53.
DeepSeekMath V2 leads in math with an average score of 79 vs 60.
DeepSeekMath V2 leads in reasoning with an average score of 76 vs 58.