Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Qwen2.5-72B wins overall with a score of 65 vs 48 (17 point difference).Qwen2.5-72B wins 4 out of 4 categories.
Llama 3 70B
56.5
Qwen2.5-72B
80.8
Llama 3 70B
50
Qwen2.5-72B
75
Llama 3 70B
57
Qwen2.5-72B
83
Llama 3 70B
55
Qwen2.5-72B
79
Qwen2.5-72B scores higher overall with 65 vs 48, a difference of 17 points across all benchmarks.
Qwen2.5-72B leads in knowledge tasks with an average score of 80.8 vs 56.5.
Qwen2.5-72B leads in coding with an average score of 75 vs 50.
Qwen2.5-72B leads in math with an average score of 83 vs 57.
Qwen2.5-72B leads in reasoning with an average score of 79 vs 55.