15:22
2026-07-24
mlq.ai
ai-safety
UK and US AI Safety Institutes Find Kimi K3 Scores 32% on Cyber Exploits vs. 76% for US Models
The UK AI Security Institute (AISI) and US Center for AI Standards and Innovation (CAISI) found that Moonshot AI's Kimi K3 scored 32% on the ExploitBench cyber benchmark, compared with 76% for leading…