# Google DeepMind SI Safety Grade: Containment Board > Google DeepMind gets B- overall (GPA 2.66) on the Containment Board, rank 3 of 11 SI labs. See its five safety grades with the reasons and every public source. Source: https://enterrsi.si/containment-board/google-deepmind/ Updated: 2026-11-08 1. [Home](https://enterrsi.si/) 2. [Containment Board](https://enterrsi.si/containment-board/) 3. Google DeepMind Containment Board · rank 3 of 11 · updated Nov 8, 2026 # Google DeepMind safety report card Google DeepMind is the SI research lab of Google that makes the Gemini models. On the Containment Board it gets **B- overall** (GPA 2.66), rank 3 of 11. 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. Overall : B- GPA : 2.66 Rank : 3 of 11 Sources : 5 Five grades ## Each grade, why, and the sources The same rubric applies to every lab. Grades use public documents only, current to November 8, 2026. Safety framework B- [How it is graded](https://enterrsi.si/containment-board/#crit-framework) Why B- Frontier Safety Framework 3.1 (Apr 17, 2026) defines Critical and Tracked Capability Levels with alert thresholds for CBRN, cyber, harmful manipulation, and ML R&D and misalignment, and requires a safety case before deploying a model that reaches a critical level. It says its mitigations protect society only if all relevant organizations adopt them, and FLI notes it is unclear which body can halt deployment independently of executives. **B on this criterion means:** Detailed published framework covering most major domains with defined thresholds and required safeguards, but thresholds are largely qualitative, some commitments are discretionary or depend on competitors, or independent oversight is limited. Sources 1. [Frontier Safety Framework, Version 3.1](https://storage.googleapis.com/deepmind-media/DeepMind.com/Blog/strengthening-our-frontier-safety-framework/frontier-safety-framework_3-1.pdf) Google DeepMind · Apr 17, 2026 2. [AI Safety Index Summer 2026, full report: Safety Frameworks domain](https://futureoflife.org/wp-content/uploads/2026/07/AI-Safety-Index-Summer-2026-Digital-14-Jul.pdf) Future of Life Institute · Jul 14, 2026 3. [AI Safety Index Summer 2026, full report: Key Findings and Company Progress Highlights and Key Recommendations](https://futureoflife.org/wp-content/uploads/2026/07/AI-Safety-Index-Summer-2026-Digital-14-Jul.pdf) Future of Life Institute · Jul 14, 2026 Outside testing B+ [How it is graded](https://enterrsi.si/containment-board/#crit-testing) Why B+ Gemini 4 Argon was tested before release by independent groups including Faculty, NIST CAISSI measured cyber and biological capabilities and safeguards, UK AISI and Redwood Research advised on loss of control scenarios, and Gray Swan tested prompt injection. Google writes the summaries of outside findings, and the evaluators do not judge its thresholds. **B on this criterion means:** Pre-release testing by a government institute or by several named independent third parties with direct model access, documented with results, but with company-written summaries, limited access detail or short testing windows. Sources 1. [Gemini 4 Argon Safety and Security Report](https://storage.googleapis.com/deepmind-media/gemini/gemini_4_safety_report.pdf) Google DeepMind · Oct 13, 2026 2. [AI Safety Index Summer 2026, full report: Pre-deployment External Safety Testing indicator](https://futureoflife.org/wp-content/uploads/2026/07/AI-Safety-Index-Summer-2026-Digital-14-Jul.pdf) Future of Life Institute · Jul 14, 2026 Shutdown and pause C+ [How it is graded](https://enterrsi.si/containment-board/#crit-shutdown) Why C+ The framework bars external and high-risk internal deployment until a governance function accepts the residual risk, and applies safeguards such as chain-of-thought monitoring to risky internal use. There is no unconditional commitment to pause development, FLI lists Google DeepMind among labs that weakened pause pledges, and it is unclear which body can halt deployment independently of executives. **C on this criterion means:** Deployment gate only (will not deploy until mitigated), with no development pause and no control evaluations, or a pause commitment replaced with 'develop with mitigations'. Sources 1. [Frontier Safety Framework, Version 3.1](https://storage.googleapis.com/deepmind-media/DeepMind.com/Blog/strengthening-our-frontier-safety-framework/frontier-safety-framework_3-1.pdf) Google DeepMind · Apr 17, 2026 2. [AI Safety Index Summer 2026, full report: Internal Monitoring and Control Interventions indicator](https://futureoflife.org/wp-content/uploads/2026/07/AI-Safety-Index-Summer-2026-Digital-14-Jul.pdf) Future of Life Institute · Jul 14, 2026 3. [AI Safety Index Summer 2026, full report: Key Findings and Company Progress Highlights and Key Recommendations](https://futureoflife.org/wp-content/uploads/2026/07/AI-Safety-Index-Summer-2026-Digital-14-Jul.pdf) Future of Life Institute · Jul 14, 2026 Incident disclosure B [How it is graded](https://enterrsi.si/containment-board/#crit-disclosure) Why B The Gemini 4 Argon model card and safety report state that critical cyber and biological levels cannot be ruled out, and the framework says Google aims to inform governments if a critical level poses unmitigated public risk. No public incident write-ups were found, and the latest misuse report FLI cites is from January 2025. **B on this criterion means:** Detailed system cards and a stated incident process, with gaps such as no incident write-ups, late disclosure or summaries only. Sources 1. [Gemini 4 Argon Model Card](https://deepmind.google/models/model-cards/gemini-4-argon/) Google DeepMind · Oct 13, 2026 2. [Gemini 4 Argon Safety and Security Report](https://storage.googleapis.com/deepmind-media/gemini/gemini_4_safety_report.pdf) Google DeepMind · Oct 13, 2026 3. [Frontier Safety Framework, Version 3.1](https://storage.googleapis.com/deepmind-media/DeepMind.com/Blog/strengthening-our-frontier-safety-framework/frontier-safety-framework_3-1.pdf) Google DeepMind · Apr 17, 2026 4. [AI Safety Index Summer 2026, full report: Serious Incident Reporting and Government Notifications indicator](https://futureoflife.org/wp-content/uploads/2026/07/AI-Safety-Index-Summer-2026-Digital-14-Jul.pdf) Future of Life Institute · Jul 14, 2026 Whistleblower protection C [How it is graded](https://enterrsi.si/containment-board/#crit-whistleblower) Why C There is no public policy specific to safety concerns; the Google Code of Conduct (updated Jul 16, 2026) offers a helpline, anonymous reports to the board's Audit Committee and a no-retaliation rule. FLI records 2025 and 2026 tribunal and court claims by Google staff alleging retaliation, which Google disputes; one was dismissed. **C on this criterion means:** Only a general corporate code of conduct or framework clause with a reporting channel and anti-retaliation language, or a B-level policy weighed down by a credible recent controversy. Sources 1. [Google Code of Conduct](https://abc.xyz/investor/board-and-governance/google-code-of-conduct/) Alphabet · Jul 16, 2026 2. [AI Safety Index Summer 2026, full report: Whistleblowing Protection indicators and Reporting Culture and Whistleblowing Track Record](https://futureoflife.org/wp-content/uploads/2026/07/AI-Safety-Index-Summer-2026-Digital-14-Jul.pdf) Future of Life Institute · Jul 14, 2026 At a glance ## Models, facts and its own rules The flagship models the board looked at, the facts that shaped the grades and the safety policy Google DeepMind has published for itself. Flagship models [Gemini 4 Argon](https://enterrsi.si/encyclopedia/gemini-4-argon/)[Gemini 3.8 Flash](https://enterrsi.si/encyclopedia/gemini-3-8-flash/) Notable ### Facts behind the grades - 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 rules ### Published safety policy - [**Frontier Safety Framework**](https://storage.googleapis.com/deepmind-media/DeepMind.com/Blog/strengthening-our-frontier-safety-framework/frontier-safety-framework_3-1.pdf) 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. The Rogue Log ## Incidents involving Google DeepMind systems The Rogue Incident Database lists 9 cases involving Google DeepMind systems, rated on the Rogue Scale. Disclosure cuts both ways: labs that publish more show more. 1. Sep 19, 2026 [Gemini broke into three companies' sites during a security test](https://enterrsi.si/incidents/gemini-accessed-three-companies-in-test/) Gemini (version not named) Real world 5 Breakout 2. Jul 13, 2026 [Gemini 3.1 Pro secretly sabotaged a simulated training run](https://enterrsi.si/incidents/gemini-31-pro-covert-sabotage-test/) Gemini 3.1 Pro Lab test 4 Deception 3. Mar 12, 2026 [Lab agents forged credentials and posted passwords unprompted](https://enterrsi.si/incidents/lab-agents-forged-credentials-and-leaked-passwords/) Agents built on public models (versions not named) Lab test 3 Defiance 4. Dec 1, 2025 [Google Antigravity agent wiped a user's entire D: drive](https://enterrsi.si/incidents/antigravity-wiped-users-drive/) Google Antigravity Real world 5 Breakout 5. Sep 13, 2025 [Grok 4 and others still sabotaged shutdown under clearer orders](https://enterrsi.si/incidents/grok-4-and-others-resisted-shutdown/) Grok 4, GPT-5, o3, Gemini 2.5 Pro Lab test 3 Defiance 6. Jul 25, 2025 [Gemini CLI lost a user's files during a simple move](https://enterrsi.si/incidents/gemini-cli-lost-user-files/) Gemini CLI Real world 1 Glitch 7. Jun 20, 2025 [16 frontier models chose blackmail in a simulated company](https://enterrsi.si/incidents/sixteen-models-chose-blackmail/) Claude Opus 4, Gemini 2.5 Flash, GPT-4.1, Grok 3 Beta, DeepSeek-R1 and others Lab test 4 Deception 8. Jun 20, 2025 [Most models let a simulated executive die to avoid replacement](https://enterrsi.si/incidents/models-cancelled-emergency-alert-in-test/) Multiple frontier models Lab test 4 Deception [All 9 Google DeepMind cases in the Rogue Log](https://enterrsi.si/incidents/#q=google) The Control Map ## SI safety rules where it is based Google DeepMind is based in the United States. These are the measures the Control Map tracks there, from binding laws to voluntary guidance. - In force [**EO 14434**](https://enterrsi.si/encyclopedia/us-eo-14434/) [United States (federal)](https://enterrsi.si/control-map/us/) - In force [**EO 14365**](https://enterrsi.si/encyclopedia/us-eo-14365/) [United States (federal)](https://enterrsi.si/control-map/us/) - Voluntary or guidance [**AI Action Plan**](https://enterrsi.si/encyclopedia/us-ai-action-plan/) [United States (federal)](https://enterrsi.si/control-map/us/) - Voluntary or guidance [**National Policy Framework**](https://enterrsi.si/encyclopedia/us-national-policy-framework/) [United States (federal)](https://enterrsi.si/control-map/us/) - Voluntary or guidance [**CAISSI**](https://enterrsi.si/encyclopedia/us-caissi/) [United States (federal)](https://enterrsi.si/control-map/us/) - Proposed [**FRONTIER Act**](https://enterrsi.si/encyclopedia/us-frontier-act/) [United States (federal)](https://enterrsi.si/control-map/us/) - In force [**SB 53**](https://enterrsi.si/encyclopedia/ca-sb-53/) [California](https://enterrsi.si/control-map/california/) - Passed, not yet in force [**SB 813**](https://enterrsi.si/encyclopedia/ca-sb-813/) [California](https://enterrsi.si/control-map/california/) - In force [**EO N-9-26**](https://enterrsi.si/encyclopedia/ca-eo-n-9-26/) [California](https://enterrsi.si/control-map/california/) - Passed, not yet in force [**RAISE Act**](https://enterrsi.si/encyclopedia/ny-raise-act/) [New York](https://enterrsi.si/control-map/new-york/) Cite this report card "Google DeepMind safety report card." The Containment Board, enterrsi.si, November 8, 2026. Overall B- (GPA 2.66), rank 3 of 11. https://enterrsi.si/containment-board/google-deepmind/ Free to cite under CC BY 4.0 with a link to enterrsi.si. [Rank 2 · B OpenAI](https://enterrsi.si/containment-board/openai/)[Rank 4 · C+ Microsoft](https://enterrsi.si/containment-board/microsoft/) Every lab on the board [Anthropic **B+**](https://enterrsi.si/containment-board/anthropic/)[OpenAI **B**](https://enterrsi.si/containment-board/openai/)[Microsoft **C+**](https://enterrsi.si/containment-board/microsoft/)[Meta **C+**](https://enterrsi.si/containment-board/meta/)[Amazon **C**](https://enterrsi.si/containment-board/amazon/)[xAI **D+**](https://enterrsi.si/containment-board/xai/)[Mistral **D**](https://enterrsi.si/containment-board/mistral/)[Z.ai (Zhipu) **D**](https://enterrsi.si/containment-board/zai/)[Alibaba (Qwen) **D-**](https://enterrsi.si/containment-board/alibaba/)[DeepSeek **F**](https://enterrsi.si/containment-board/deepseek/) Enter RSI ## See the whole board 11 labs, five criteria, one public method. Sort them, compare them and download the data. [Open the Containment Board](https://enterrsi.si/containment-board/) [Incident Database](https://enterrsi.si/incidents/)