Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5.4 wins overall with a score of 88 vs 61 (27 point difference).GPT-5.4 wins 4 out of 4 categories.
GPT-5.4
96
Mistral Large 3
73.8
GPT-5.4
91
Mistral Large 3
68
GPT-5.4
97.1
Mistral Large 3
75
GPT-5.4
94
Mistral Large 3
72
GPT-5.4 scores higher overall with 88 vs 61, a difference of 27 points across all benchmarks.
GPT-5.4 leads in knowledge tasks with an average score of 96 vs 73.8.
GPT-5.4 leads in coding with an average score of 91 vs 68.
GPT-5.4 leads in math with an average score of 97.1 vs 75.
GPT-5.4 leads in reasoning with an average score of 94 vs 72.