Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Llama 3.1 405B wins overall with a score of 58 vs 46 (12 point difference).Llama 3.1 405B wins 4 out of 4 categories.
Claude 3 Haiku
54.5
Llama 3.1 405B
68.5
Claude 3 Haiku
48
Llama 3.1 405B
62
Claude 3 Haiku
55
Llama 3.1 405B
69
Claude 3 Haiku
53
Llama 3.1 405B
67
Llama 3.1 405B scores higher overall with 58 vs 46, a difference of 12 points across all benchmarks.
Llama 3.1 405B leads in knowledge tasks with an average score of 68.5 vs 54.5.
Llama 3.1 405B leads in coding with an average score of 62 vs 48.
Llama 3.1 405B leads in math with an average score of 69 vs 55.
Llama 3.1 405B leads in reasoning with an average score of 67 vs 53.