Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Llama 3 70B wins overall with a score of 48 vs 27 (21 point difference).Llama 3 70B wins 4 out of 4 categories.
Llama 3 70B
56.5
MiniMax M1 80k
33.8
Llama 3 70B
50
MiniMax M1 80k
28
Llama 3 70B
57
MiniMax M1 80k
35
Llama 3 70B
55
MiniMax M1 80k
33
Llama 3 70B scores higher overall with 48 vs 27, a difference of 21 points across all benchmarks.
Llama 3 70B leads in knowledge tasks with an average score of 56.5 vs 33.8.
Llama 3 70B leads in coding with an average score of 50 vs 28.
Llama 3 70B leads in math with an average score of 57 vs 35.
Llama 3 70B leads in reasoning with an average score of 55 vs 33.