Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5.2 wins overall with a score of 83 vs 58 (25 point difference).GPT-5.2 wins 4 out of 4 categories.
GPT-5.2
96
Llama 3.1 405B
68.5
GPT-5.2
91
Llama 3.1 405B
62
GPT-5.2
97.1
Llama 3.1 405B
69
GPT-5.2
94
Llama 3.1 405B
67
GPT-5.2 scores higher overall with 83 vs 58, a difference of 25 points across all benchmarks.
GPT-5.2 leads in knowledge tasks with an average score of 96 vs 68.5.
GPT-5.2 leads in coding with an average score of 91 vs 62.
GPT-5.2 leads in math with an average score of 97.1 vs 69.
GPT-5.2 leads in reasoning with an average score of 94 vs 67.