Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeekMath V2 wins overall with a score of 64 vs 42 (22 point difference).DeepSeekMath V2 wins 4 out of 4 categories.
DeepSeekMath V2
77.8
GPT-OSS 120B
48.8
DeepSeekMath V2
72
GPT-OSS 120B
43
DeepSeekMath V2
79
GPT-OSS 120B
50
DeepSeekMath V2
76
GPT-OSS 120B
48
DeepSeekMath V2 scores higher overall with 64 vs 42, a difference of 22 points across all benchmarks.
DeepSeekMath V2 leads in knowledge tasks with an average score of 77.8 vs 48.8.
DeepSeekMath V2 leads in coding with an average score of 72 vs 43.
DeepSeekMath V2 leads in math with an average score of 79 vs 50.
DeepSeekMath V2 leads in reasoning with an average score of 76 vs 48.