{"slug": "cogent-s-vr-1-1-repairs-57-9-of-livecvebench-tasks-in-company-run", "title": "Cogent's VR-1.1 repairs 57.9% of LiveCVEBench tasks in company run", "summary": "Cogent Security released VR-1.1 on November 3rd, 2026, a security reasoning model tuned for vulnerability repair, and reported that it fixed 57.9% of 190 LiveCVEBench tasks in the company's own run, 12.6 percentage points ahead of Claude Code and Codex at 45.3% each. Founders Vineet Edupuganti and Geng Sng built Cogent around the gap between fast AI-driven vulnerability discovery and slower patching, betting that a trustworthy fix is the scarce step.", "body_md": "# Cogent's VR-1.1 repairs 57.9% of LiveCVEBench tasks in company run\n\n**Vineet Edupuganti and Geng Sng's Cogent Security reports that VR-1.1 repaired 57.9% of 190 LiveCVEBench tasks, 12.6 percentage points ahead of Claude Code and Codex in its own run.**\n\n        By [Ryan Merket](https://runtimewire.com/author/ryan-merket)\n        · Published \n\nPrimary source: [PR Newswire Business Technology](https://www.prnewswire.com/news-releases/cogent-unveils-vr-1-1--its-latest-frontier-cyber-model-which-tops-livecvebench-for-vulnerability-repair-302927966.html)\n\n## Why it matters\n\nAI-driven disclosure is producing vulnerabilities faster than engineers can safely patch them, and Cogent's founders are betting the scarce step is a trustworthy fix.\n\nVineet Edupuganti and Geng Sng built Cogent Security around a bottleneck they watched at Abnormal Security: finding vulnerabilities was getting faster, and fixing them was not. On November 3rd, 2026, Cogent released VR-1.1, a version of its security reasoning model tuned for repair, and reported in [Cogent's LiveCVEBench research post](https://www.cogent.com/blog/vr-1.1-on-livecvebench-remediating-real-vulnerabilities?ref=runtimewire) that it fixed 57.9% of 190 tasks, compared with 45.3% for both Claude Code and Codex.…\n\nWhen you purchase through links in our articles, [we may earn a small commission](https://runtimewire.com/affiliate-monetization-standards). This doesn’t affect our editorial independence.", "url": "https://wpnews.pro/news/cogent-s-vr-1-1-repairs-57-9-of-livecvebench-tasks-in-company-run", "canonical_source": "https://runtimewire.com/article/cogent-vr-1-1-livecvebench-vulnerability-repair", "published_at": "2026-11-03 15:46:08+00:00", "updated_at": "2026-11-03 18:49:26.974407+00:00", "lang": "en", "topics": ["ai-safety", "artificial-intelligence", "ai-products"], "entities": ["Cogent Security", "VR-1.1", "LiveCVEBench", "Vineet Edupuganti", "Geng Sng", "Claude Code", "Codex", "Abnormal Security"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/cogent-s-vr-1-1-repairs-57-9-of-livecvebench-tasks-in-company-run", "markdown": "https://wpnews.pro/news/cogent-s-vr-1-1-repairs-57-9-of-livecvebench-tasks-in-company-run.md", "text": "https://wpnews.pro/news/cogent-s-vr-1-1-repairs-57-9-of-livecvebench-tasks-in-company-run.txt", "jsonld": "https://wpnews.pro/news/cogent-s-vr-1-1-repairs-57-9-of-livecvebench-tasks-in-company-run.jsonld"}}