The preliminary US-UK joint assessment found Kimi K3 performed below the most recent frontier cyber-capable models on several offensive cybersecurity tasks and failed to achieve arbitrary code execution in ExploitBench tests. The evaluation comes amid growing U.S. scrutiny of China’s latest open-weight AI model.
China’s Kimi K3 Lags Top U.S. Frontier AI Models in Cybersecurity Tests: US CAISI, UK AISI