Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Kimi K2.5 wins overall with a score of 62 vs 50 (12 point difference).Kimi K2.5 wins 4 out of 4 categories.
GPT-4 Turbo
58.5
Kimi K2.5
74.8
GPT-4 Turbo
52
Kimi K2.5
69
GPT-4 Turbo
59
Kimi K2.5
76
GPT-4 Turbo
57
Kimi K2.5
73
Kimi K2.5 scores higher overall with 62 vs 50, a difference of 12 points across all benchmarks.
Kimi K2.5 leads in knowledge tasks with an average score of 74.8 vs 58.5.
Kimi K2.5 leads in coding with an average score of 69 vs 52.
Kimi K2.5 leads in math with an average score of 76 vs 59.
Kimi K2.5 leads in reasoning with an average score of 73 vs 57.