Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Llama 3 70B wins overall with a score of 48 vs 37 (11 point difference).Llama 3 70B wins 4 out of 4 categories.
Llama 3 70B
56.5
Llama 4 Maverick
43.8
Llama 3 70B
50
Llama 4 Maverick
38
Llama 3 70B
57
Llama 4 Maverick
45
Llama 3 70B
55
Llama 4 Maverick
43
Llama 3 70B scores higher overall with 48 vs 37, a difference of 11 points across all benchmarks.
Llama 3 70B leads in knowledge tasks with an average score of 56.5 vs 43.8.
Llama 3 70B leads in coding with an average score of 50 vs 38.
Llama 3 70B leads in math with an average score of 57 vs 45.
Llama 3 70B leads in reasoning with an average score of 55 vs 43.