Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Kimi K2.5 wins overall with a score of 62 vs 42 (20 point difference).Kimi K2.5 wins 4 out of 4 categories.
GPT-OSS 120B
48.8
Kimi K2.5
74.8
GPT-OSS 120B
43
Kimi K2.5
69
GPT-OSS 120B
50
Kimi K2.5
76
GPT-OSS 120B
48
Kimi K2.5
73
Kimi K2.5 scores higher overall with 62 vs 42, a difference of 20 points across all benchmarks.
Kimi K2.5 leads in knowledge tasks with an average score of 74.8 vs 48.8.
Kimi K2.5 leads in coding with an average score of 69 vs 43.
Kimi K2.5 leads in math with an average score of 76 vs 50.
Kimi K2.5 leads in reasoning with an average score of 73 vs 48.