Cluster Tests

Assessment of LLM agents creating hardened Kubernetes clusters using Kind. Each model was given 10 minutes to create a cluster with comprehensive security controls including audit logging, Pod Security Standards, network policies, API server hardening, and kubelet hardening.

Original date: 2026-03-09 | Re-run date: 2026-03-10 | Claude Opus 4.6 added: 2026-03-25 | MiniMax M2.7 added: 2026-03-28 | Claude Opus 4.7 added: 2026-04-20 | Qwen 3.6 Plus added: 2026-04-20 | DeepSeek V4 Pro added: 2026-04-24 | DeepSeek V4 Flash added: 2026-04-24 | DeepSeek V4 Flash 0731 added: 2026-08-01 Google Gemini 3.7 Flash added: 2026-08-14 Qwen 3.8 27B added: 2026-08-19 Models: Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, GPT 5.4, Gemini 3 Flash Preview, Gemini 3.7 Flash, Qwen 3.6 Plus, Qwen 3.8 27B, DeepSeek V4 Pro, DeepSeek V4 Flash, DeepSeek V4 Flash 0731, MiniMax M2.7, MiniMax M2.5, DeepSeek V3.2


Table of contents


Back to top

Dearbhadh — LLM Kubernetes Security Assessment Tool

This site uses Just the Docs, a documentation theme for Jekyll.