Google DeepMind

Google DeepMind is the SI research lab of Google that makes the Gemini models. Its Containment Board grade is B- (GPA 2.66), rank 3 of 11.

Overall grade: B-
Board rank: 3 of 11
Models listed: 7
Rogue Log cases: 9

The lab

Google DeepMind is the SI research lab of Google that makes the Gemini models. Google DeepMind publishes a detailed Frontier Safety Framework and a 217-page safety report for Gemini 4 Argon that says it cannot rule out critical cyber and biological capability. Outside testing is broad but summarized by Google, its framework ties full protection to the rest of the industry, and it has no public whistleblower policy specific to safety.

Safety grades

On the Containment Board Google DeepMind gets B- overall (GPA 2.66), rank 3 of 11. Each grade, its reasons and its sources are on the Google DeepMind report card.

Safety frameworkB-
Outside testingB+
Shutdown and pauseC+
Incident disclosureB
Whistleblower protectionC

Notable facts

Google DeepMind says it cannot rule out that Gemini 4 Argon reached its cybersecurity Critical Capability Level and estimates unmitigated access could cut the cost of severe historical cyberattacks by about 16.7 times on average.
Gemini 4 Argon passed 14 of 15 stealth and situational awareness challenges, so Google could not rule out the matching Tracked Capability Level.

Its own safety policy

Frontier Safety Framework Version 3.1, updated Apr 17, 2026
Sets Critical Capability Levels for CBRN, cyber, harmful manipulation and ML R&D, and adds Tracked Capability Levels, including one for stealth and situational awareness tied to misalignment. Reaching a Critical Capability Level requires a safety case and governance approval before external or high-risk internal deployment.