Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5.2 wins overall with a score of 83 vs 24 (59 point difference).GPT-5.2 wins 4 out of 4 categories.
DeepSeek V3.1
30.8
GPT-5.2
96
DeepSeek V3.1
25
GPT-5.2
91
DeepSeek V3.1
32
GPT-5.2
97.1
DeepSeek V3.1
30
GPT-5.2
94
GPT-5.2 scores higher overall with 83 vs 24, a difference of 59 points across all benchmarks.
GPT-5.2 leads in knowledge tasks with an average score of 96 vs 30.8.
GPT-5.2 leads in coding with an average score of 91 vs 25.
GPT-5.2 leads in math with an average score of 97.1 vs 32.
GPT-5.2 leads in reasoning with an average score of 94 vs 30.