On a private cybersecurity benchmark, Kimi K3 emerged as the workhorse at near-frontier recall for a fraction of the cost, GPT-5.6 Sol took the crown at seven times the price — and Fable 5 refused 100% of the tasks, turning safety into a service outage.
Moonshot’s chief executive calls a pure reasoning model a fish tank with a brain in it, and states the endgame plainly: we want K2 to help build K3.