Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5.3 Codex wins overall with a score of 85 vs 70 (15 point difference).GPT-5.3 Codex wins 4 out of 4 categories.
GPT-5.3 Codex
96
Qwen3.5 397B (Reasoning)
88
GPT-5.3 Codex
95
Qwen3.5 397B (Reasoning)
83
GPT-5.3 Codex
97.1
Qwen3.5 397B (Reasoning)
92
GPT-5.3 Codex
94
Qwen3.5 397B (Reasoning)
86
GPT-5.3 Codex scores higher overall with 85 vs 70, a difference of 15 points across all benchmarks.
GPT-5.3 Codex leads in knowledge tasks with an average score of 96 vs 88.
GPT-5.3 Codex leads in coding with an average score of 95 vs 83.
GPT-5.3 Codex leads in math with an average score of 97.1 vs 92.
GPT-5.3 Codex leads in reasoning with an average score of 94 vs 86.