Tech · 5 d ago
Austin McKinley · CC BY 3.0 · Wikimedia Commons
Google's Gemini 4 Carbon leads benchmarks for finding and fixing security flaws
Google says Gemini 4 Carbon scores 88.2 per cent on SEC-bench Pro for finding vulnerabilities, 54.8 per cent on ExploitGym for exploitation and 71.0 per cent on CWE-bench for patching.
Intelligence Index scores
- 1 Gemini 4 Carbon: 59
- 2 Claude Opus 5.5: 58
- 3 GPT-6 Astra: 57
- 4 GPT-6.1 Sol: 55
On the Artificial Analysis Intelligence Index, Carbon scores 59, ahead of Anthropic's Claude Opus 5.5 at 58 and OpenAI's GPT-6 Astra at 57.
Access starts with a subset of cyber defenders and will widen to trusted partners. Google says Carbon is twice as likely to produce secure code as Gemini 4 Argon, released less than a week earlier.
