thehackernews.com
Google’s Gemini 4 Carbon Leads Benchmarks for Finding, Exploiting, and Patching Vulnerabilities
Google unveiled Gemini 4 Carbon, a new frontier model optimized for cybersecurity tasks. The model achieved top scores on three key benchmarks: 88.2 % on SEC‑bench Pro for vulnerability discovery, 54.8 % on ExploitGym for exploit generation, and 71.0 % on CWE‑bench for patch remediation. On the Artificial Analysis Intelligence Index, Carbon led with a score of 59, edging out Anthropic’s Claude Opus 5.5, OpenAI’s GPT‑6 Astra and GPT‑6.1 Sol. Carbon also produces secure code at twice the rate of its predecessor Argon and resists indirect prompt‑injection [...]