Kimi K3 finds 16 new vulnerabilities and beats GLM-5.2 on an exploit benchmark

zephyr_z9 · x · 2026-07-28

Kimi K3’s cyber report shows 16 new bugs and better exploit performance than GLM-5.2

The Kimi K3 tech report says the model found 16 previously unknown vulnerabilities across six projects, including two Linux kernel bugs: a remotely triggerable DoS and a local privilege-escalation issue.

On an exploit-development suite, Kimi K3 solved 14/36 tasks (38.9%) versus 8/36 (22.2%) for GLM-5.2. But the gains were uneven: 10 of Kimi’s 14 wins came from the user-space track, and both models failed about three quarters of the kernel track. The report also notes that the remaining misses cluster around incomplete exploit chains, poor strategy selection under mitigations, unproductive debugging loops, and insufficient final verification.

Original post →

More from Models

Models channel →