Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5 (medium) wins overall with a score of 70 vs 64 (6 point difference).GPT-5 (medium) wins 4 out of 4 categories.
DeepSeekMath V2
77.8
GPT-5 (medium)
88
DeepSeekMath V2
72
GPT-5 (medium)
83
DeepSeekMath V2
79
GPT-5 (medium)
92
DeepSeekMath V2
76
GPT-5 (medium)
86
GPT-5 (medium) scores higher overall with 70 vs 64, a difference of 6 points across all benchmarks.
GPT-5 (medium) leads in knowledge tasks with an average score of 88 vs 77.8.
GPT-5 (medium) leads in coding with an average score of 83 vs 72.
GPT-5 (medium) leads in math with an average score of 92 vs 79.
GPT-5 (medium) leads in reasoning with an average score of 86 vs 76.