Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5.4 wins overall with a score of 88 vs 48 (40 point difference).GPT-5.4 wins 4 out of 4 categories.
GPT-5.4
96
Llama 3 70B
56.5
GPT-5.4
91
Llama 3 70B
50
GPT-5.4
97.1
Llama 3 70B
57
GPT-5.4
94
Llama 3 70B
55
GPT-5.4 scores higher overall with 88 vs 48, a difference of 40 points across all benchmarks.
GPT-5.4 leads in knowledge tasks with an average score of 96 vs 56.5.
GPT-5.4 leads in coding with an average score of 91 vs 50.
GPT-5.4 leads in math with an average score of 97.1 vs 57.
GPT-5.4 leads in reasoning with an average score of 94 vs 55.