Back to news

AI · Article

Security-Only AI Agent VR-1.1 Tops Claude and GPT on Vulnerability Benchmark

디일렉 ·

At a glance

Cogent Security, a US startup, released VR-1.1, an AI model built for security work. It scored higher than Anthropic and OpenAI models on one specific security benchmark. However, its cost efficiency was lower, and this result alone is not enough to call it overall better.

Key points

Why it matters

How accurately and quickly AI can find and fix security vulnerabilities is directly tied to real-world hacking defense capability.

Original source

GPT·클로드 제친 보안 전용 AI 에이전트 등장

디일렉 · Nov 6, 17:58 KST

Read on 디일렉 ↗

AI summarized the original article. Check the original for accuracy. Copyright belongs to 디일렉.

Claude · Ranking and more news