Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeekMath V2 wins overall with a score of 64 vs 61 (3 point difference).DeepSeekMath V2 wins 4 out of 4 categories.
DeepSeekMath V2
77.8
Mistral Large 3
73.8
DeepSeekMath V2
72
Mistral Large 3
68
DeepSeekMath V2
79
Mistral Large 3
75
DeepSeekMath V2
76
Mistral Large 3
72
DeepSeekMath V2 scores higher overall with 64 vs 61, a difference of 3 points across all benchmarks.
DeepSeekMath V2 leads in knowledge tasks with an average score of 77.8 vs 73.8.
DeepSeekMath V2 leads in coding with an average score of 72 vs 68.
DeepSeekMath V2 leads in math with an average score of 79 vs 75.
DeepSeekMath V2 leads in reasoning with an average score of 76 vs 72.