Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeekMath V2 wins overall with a score of 64 vs 40 (24 point difference).DeepSeekMath V2 wins 4 out of 4 categories.
DeepSeekMath V2
77.8
Nemotron Ultra 253B
46.8
DeepSeekMath V2
72
Nemotron Ultra 253B
41
DeepSeekMath V2
79
Nemotron Ultra 253B
48
DeepSeekMath V2
76
Nemotron Ultra 253B
46
DeepSeekMath V2 scores higher overall with 64 vs 40, a difference of 24 points across all benchmarks.
DeepSeekMath V2 leads in knowledge tasks with an average score of 77.8 vs 46.8.
DeepSeekMath V2 leads in coding with an average score of 72 vs 41.
DeepSeekMath V2 leads in math with an average score of 79 vs 48.
DeepSeekMath V2 leads in reasoning with an average score of 76 vs 46.