Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeekMath V2 wins overall with a score of 64 vs 38 (26 point difference).DeepSeekMath V2 wins 4 out of 4 categories.
DeepSeekMath V2
77.8
Llama 4 Scout
44.8
DeepSeekMath V2
72
Llama 4 Scout
39
DeepSeekMath V2
79
Llama 4 Scout
46
DeepSeekMath V2
76
Llama 4 Scout
44
DeepSeekMath V2 scores higher overall with 64 vs 38, a difference of 26 points across all benchmarks.
DeepSeekMath V2 leads in knowledge tasks with an average score of 77.8 vs 44.8.
DeepSeekMath V2 leads in coding with an average score of 72 vs 39.
DeepSeekMath V2 leads in math with an average score of 79 vs 46.
DeepSeekMath V2 leads in reasoning with an average score of 76 vs 44.