Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5.1 wins overall with a score of 76 vs 64 (12 point difference).GPT-5.1 wins 4 out of 4 categories.
DeepSeekMath V2
77.8
GPT-5.1
94
DeepSeekMath V2
72
GPT-5.1
89
DeepSeekMath V2
79
GPT-5.1
97.1
DeepSeekMath V2
76
GPT-5.1
92
GPT-5.1 scores higher overall with 76 vs 64, a difference of 12 points across all benchmarks.
GPT-5.1 leads in knowledge tasks with an average score of 94 vs 77.8.
GPT-5.1 leads in coding with an average score of 89 vs 72.
GPT-5.1 leads in math with an average score of 97.1 vs 79.
GPT-5.1 leads in reasoning with an average score of 92 vs 76.