Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5.3 Codex wins overall with a score of 85 vs 80 (5 point difference).GPT-5.3 Codex wins 1 out of 4 categories.
Claude Sonnet 4.6
96
GPT-5.3 Codex
96
Claude Sonnet 4.6
93
GPT-5.3 Codex
95
Claude Sonnet 4.6
97.1
GPT-5.3 Codex
97.1
Claude Sonnet 4.6
94
GPT-5.3 Codex
94
GPT-5.3 Codex scores higher overall with 85 vs 80, a difference of 5 points across all benchmarks.
Claude Sonnet 4.6 and GPT-5.3 Codex are tied for knowledge tasks with average scores of 96.
GPT-5.3 Codex leads in coding with an average score of 95 vs 93.
Claude Sonnet 4.6 and GPT-5.3 Codex are tied for math with average scores of 97.1.
Claude Sonnet 4.6 and GPT-5.3 Codex are tied for reasoning with average scores of 94.