Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Gemini 3.1 Pro wins overall with a score of 87 vs 82 (5 point difference).Gemini 3.1 Pro wins 0 out of 4 categories.
Gemini 3.1 Pro
96
GPT-5.2-Codex
96
Gemini 3.1 Pro
91
GPT-5.2-Codex
95
Gemini 3.1 Pro
97.1
GPT-5.2-Codex
97.1
Gemini 3.1 Pro
94
GPT-5.2-Codex
94
Gemini 3.1 Pro scores higher overall with 87 vs 82, a difference of 5 points across all benchmarks.
Gemini 3.1 Pro and GPT-5.2-Codex are tied for knowledge tasks with average scores of 96.
GPT-5.2-Codex leads in coding with an average score of 95 vs 91.
Gemini 3.1 Pro and GPT-5.2-Codex are tied for math with average scores of 97.1.
Gemini 3.1 Pro and GPT-5.2-Codex are tied for reasoning with average scores of 94.