Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5 mini wins overall with a score of 68 vs 39 (29 point difference).GPT-5 mini wins 4 out of 4 categories.
GPT-5 mini
85
Llama 4 Behemoth
45.8
GPT-5 mini
80
Llama 4 Behemoth
40
GPT-5 mini
89
Llama 4 Behemoth
47
GPT-5 mini
83
Llama 4 Behemoth
45
GPT-5 mini scores higher overall with 68 vs 39, a difference of 29 points across all benchmarks.
GPT-5 mini leads in knowledge tasks with an average score of 85 vs 45.8.
GPT-5 mini leads in coding with an average score of 80 vs 40.
GPT-5 mini leads in math with an average score of 89 vs 47.
GPT-5 mini leads in reasoning with an average score of 83 vs 45.