Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5.2 wins overall with a score of 83 vs 80 (3 point difference).GPT-5.2 wins 0 out of 4 categories.
Claude Sonnet 4.6
96
GPT-5.2
96
Claude Sonnet 4.6
93
GPT-5.2
91
Claude Sonnet 4.6
97.1
GPT-5.2
97.1
Claude Sonnet 4.6
94
GPT-5.2
94
GPT-5.2 scores higher overall with 83 vs 80, a difference of 3 points across all benchmarks.
Claude Sonnet 4.6 and GPT-5.2 are tied for knowledge tasks with average scores of 96.
Claude Sonnet 4.6 leads in coding with an average score of 93 vs 91.
Claude Sonnet 4.6 and GPT-5.2 are tied for math with average scores of 97.1.
Claude Sonnet 4.6 and GPT-5.2 are tied for reasoning with average scores of 94.