Kimi K3 Ranks Second on AA-Briefcase Despite High Costs and Slow Speeds

Kimi K3: second only to Fable 5 on AA-Briefcase

Kimi K3 achieves the second-highest score on our AA-Briefcase benchmark, trailing only Fable 5 with strong analytical capabilities. However, this performance comes at a steep price, costing over ten dollars per task and averaging nearly an hour to complete. While it outperforms models like GPT-5.6 Sol in correctness, its presentation quality and speed lag behind competitors, raising questions about its practical efficiency.