Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5 (high) wins overall with a score of 72 vs 39 (33 point difference).GPT-5 (high) wins 4 out of 4 categories.
GPT-5 (high)
90
Llama 4 Behemoth
45.8
GPT-5 (high)
85
Llama 4 Behemoth
40
GPT-5 (high)
94
Llama 4 Behemoth
47
GPT-5 (high)
88
Llama 4 Behemoth
45
GPT-5 (high) scores higher overall with 72 vs 39, a difference of 33 points across all benchmarks.
GPT-5 (high) leads in knowledge tasks with an average score of 90 vs 45.8.
GPT-5 (high) leads in coding with an average score of 85 vs 40.
GPT-5 (high) leads in math with an average score of 94 vs 47.
GPT-5 (high) leads in reasoning with an average score of 88 vs 45.