Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Kimi K2.5 wins overall with a score of 62 vs 48 (14 point difference).Kimi K2.5 wins 4 out of 4 categories.
Kimi K2.5
74.8
Llama 3 70B
56.5
Kimi K2.5
69
Llama 3 70B
50
Kimi K2.5
76
Llama 3 70B
57
Kimi K2.5
73
Llama 3 70B
55
Kimi K2.5 scores higher overall with 62 vs 48, a difference of 14 points across all benchmarks.
Kimi K2.5 leads in knowledge tasks with an average score of 74.8 vs 56.5.
Kimi K2.5 leads in coding with an average score of 69 vs 50.
Kimi K2.5 leads in math with an average score of 76 vs 57.
Kimi K2.5 leads in reasoning with an average score of 73 vs 55.