Google reported that Gemini 4 Carbon scored 88.2% on the SEC-bench Pro vulnerability-finding benchmark with its safety guardrails turned off

Google DeepMind's frontier AI model, released on October 28, 2026, two weeks after Gemini 4 Argon's wide rollout, first only to selected cybersecurity defenders through Google's Fairwind Program; it ranked first on the Artificial Analysis Intelligence Index v5 with a score of 59.