Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Llama 3 70B wins overall with a score of 48 vs 43 (5 point difference).Llama 3 70B wins 4 out of 4 categories.
Llama 3 70B
56.5
Z-1
49.8
Llama 3 70B
50
Z-1
44
Llama 3 70B
57
Z-1
51
Llama 3 70B
55
Z-1
49
Llama 3 70B scores higher overall with 48 vs 43, a difference of 5 points across all benchmarks.
Llama 3 70B leads in knowledge tasks with an average score of 56.5 vs 49.8.
Llama 3 70B leads in coding with an average score of 50 vs 44.
Llama 3 70B leads in math with an average score of 57 vs 51.
Llama 3 70B leads in reasoning with an average score of 55 vs 49.