Safety · The Decoder ·
Kimi K3 trails frontier US models by a wide margin on cyber exploits, and distillation may explain why
Tests by the British AI Security Institute and the U.S. Center for AI Standards and Innovation found Moonshot AI’s Kimi K3 scored 32% on ExploitBench, versus 76% for leading U.S. models. Its safeguards also failed to block exploit development and simulated attacks; the article links the gap to reported model distillati