🧰 Grok 4.5

The items that name it 4

• Introducing dfbench v1: A cybersecurity benchmark for frontier models and agentic systems | depthfirst
  articleas affected products2026-08-19It is written here as Grok 4.5 (evaluated model).

  evaluated model

• XBOW: Grok 4.5 Is Powerful. The System Around It Makes It Safe.
  articleas affected products2026-08-08
• Benchmarking 13 AI models on rediscovering known CVEs
  articleas tools2026-07-16It is written here as grok-4.5.

  xAI model benchmarked; second-highest recall at 20/26

• XBOW: Grok 4.5 Poised To Take Over the Middle of the AI Security Market
  articleas tools2026-07-16

  AI model evaluated for offensive security / cybersecurity agentic tasks (exploit crafting, vulnerability solving); released the day before this post

In every workspace you can read 8