Exclusive: Cogent Security’s VR-1.1 model outscores Claude Code and Codex on vulnerability repair
Vulnerability management startup Cogent Security unveiled VR-1.1, a new version of its frontier reasoning model designed to automatically write fixes for newly disclosed software vulnerabilities. According to the announcement, the model achieved superior performance compared to Anthropic's Claude Code and OpenAI's Codex on a public repair benchmark. The release targets vulnerability management workflows that have historically been slow to automate.
Key points
- VR-1.1 model outscored Claude Code and Codex on vulnerability repair benchmarks
- Model writes automated fixes for newly disclosed software vulnerabilities
- Represents advancement in automating a previously slow area of vulnerability management
Summary and key points written by AI from the headline and a short excerpt, so they can be incomplete or wrong. SiliconANGLE did the reporting; read the original for the full story.
Read the full story at SiliconANGLE
