Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Kimi K2.5 wins overall with a score of 62 vs 45 (17 point difference).Kimi K2.5 wins 4 out of 4 categories.
Kimi K2.5
74.8
Nemotron-4 15B
51.8
Kimi K2.5
69
Nemotron-4 15B
46
Kimi K2.5
76
Nemotron-4 15B
53
Kimi K2.5
73
Nemotron-4 15B
51
Kimi K2.5 scores higher overall with 62 vs 45, a difference of 17 points across all benchmarks.
Kimi K2.5 leads in knowledge tasks with an average score of 74.8 vs 51.8.
Kimi K2.5 leads in coding with an average score of 69 vs 46.
Kimi K2.5 leads in math with an average score of 76 vs 53.
Kimi K2.5 leads in reasoning with an average score of 73 vs 51.