# DeepSeek SI Safety Grade: Containment Board > DeepSeek gets F overall (GPA 0.34) on the Containment Board, rank 11 of 11. Best on incident disclosure, weakest on outside testing, every grade sourced. Source: https://enterrsi.si/containment-board/deepseek/ Updated: 2026-11-08 1. [Home](https://enterrsi.si/) 2. [Containment Board](https://enterrsi.si/containment-board/) 3. DeepSeek Containment Board · rank 11 of 11 · updated Nov 8, 2026 # DeepSeek safety report card DeepSeek is a Chinese SI developer that makes the DeepSeek models. On the Containment Board it gets **F overall** (GPA 0.34), rank 11 of 11. DeepSeek ships frontier-class open-weight models without a published safety framework, outside pre-release testing, shutdown commitments or a whistleblower policy. Its incident duties come from Chinese law, and US CAISSI's evaluation of DeepSeek V4 Pro was run on the released model. Overall : F GPA : 0.34 Rank : 11 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 D- [How it is graded](https://enterrsi.si/containment-board/#crit-framework) Why D- No published frontier safety framework was found; DeepSeek signed the safety commitments of the China Academy of Information and Communications Technology (CAICT) but not the Seoul commitments. **D on this criterion means:** No framework of its own; the lab has only signed voluntary pledges such as the Seoul Frontier AI Safety Commitments, the EU General-Purpose AI Code of Practice or China's CAICT commitments. Sources 1. [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 2. [AI Safety Index Summer 2026, full report: Voluntary Commitment indicators (Seoul commitments, EU Code of Practice)](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. [Frontier AI Safety Policies (index of published company frameworks)](https://metr.org/fsp) METR · Nov 8, 2026 Outside testing F [How it is graded](https://enterrsi.si/containment-board/#crit-testing) Why F No outside pre-release testing was found (FLI: no public mention). US CAISSI evaluated DeepSeek V4 Pro after release and found it about eight months behind the US frontier; post-release government testing earns no credit here. **F on this criterion means:** No commitment and no evidence of pre-release outside testing. Government testing after release without the lab's involvement is noted but earns no credit. Sources 1. [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 2. [CAISI Evaluation of DeepSeek V4 Pro](https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro) NIST · May 1, 2026 3. [AI Safety Index, Summer 2026 Edition (scorecard)](https://futureoflife.org/ai-safety-index-summer-2026/) Future of Life Institute · Jul 7, 2026 Shutdown and pause F [How it is graded](https://enterrsi.si/containment-board/#crit-shutdown) Why F No public commitment to pause or shut down and no monitoring and control plan for internal deployment were found as of Nov 8, 2026. **F on this criterion means:** No public commitment found. Sources 1. [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 2. [DeepSeek-V4.1-Flash-1017 release notes (with release history)](https://api-docs.deepseek.com/news/news261017) DeepSeek · Oct 17, 2026 Incident disclosure D [How it is graded](https://enterrsi.si/containment-board/#crit-disclosure) Why D Release notes focus on capabilities, and incident reporting rests on Chinese legal duties to remove unlawful content and report incidents to regulators, which do not cover frontier safety events. **D on this criterion means:** Minimal safety documentation; incident reporting only where the law requires it. Sources 1. [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 2. [DeepSeek-V4.1-Flash-1017 release notes (with release history)](https://api-docs.deepseek.com/news/news261017) DeepSeek · Oct 17, 2026 Whistleblower protection F [How it is graded](https://enterrsi.si/containment-board/#crit-whistleblower) Why F No public whistleblower policy was found, and FLI found no public record of whistleblower cases either way. **F on this criterion means:** No whistleblower policy or reporting channel found in public sources. Sources 1. [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 DeepSeek has published for itself. Flagship models [DeepSeek-V4-Pro](https://enterrsi.si/encyclopedia/deepseek-v4-pro/)[DeepSeek-V4.1-Flash](https://enterrsi.si/encyclopedia/deepseek-v4-1-flash/) Notable ### Facts behind the grades - US CAISSI found DeepSeek V4 Pro scored lower on its tests, which include non-public benchmarks, than on DeepSeek's self-reported results. - FLI's Summer 2026 index graded DeepSeek F overall. Its own rules ### Published safety policy The Control Map lists no frontier safety framework of its own for DeepSeek. Its safety framework grade above explains what the board found instead. The Rogue Log ## Incidents involving DeepSeek systems The Rogue Incident Database lists 3 cases involving DeepSeek systems, rated on the Rogue Scale. Disclosure cuts both ways: labs that publish more show more. 1. 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 2. 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 3. Feb 18, 2025 [Reasoning models hacked a chess game instead of playing it](https://enterrsi.si/incidents/reasoning-models-hacked-chess-game/) o1-preview, DeepSeek R1 Lab test 2 Workaround The Control Map ## SI safety rules where it is based DeepSeek is based in China. These are the measures the Control Map tracks there, from binding laws to voluntary guidance. - In force [**Generative AI Measures**](https://enterrsi.si/encyclopedia/cn-generative-measures/) [China](https://enterrsi.si/control-map/china/) - In force [**Labeling Measures**](https://enterrsi.si/encyclopedia/cn-labeling-measures/) [China](https://enterrsi.si/control-map/china/) - In force [**Cybersecurity Law SI clause**](https://enterrsi.si/encyclopedia/cn-cybersecurity-law-amendment/) [China](https://enterrsi.si/control-map/china/) - Voluntary or guidance [**Framework 3.0**](https://enterrsi.si/encyclopedia/cn-ai-safety-governance-framework/) [China](https://enterrsi.si/control-map/china/) Cite this report card "DeepSeek safety report card." The Containment Board, enterrsi.si, November 8, 2026. Overall F (GPA 0.34), rank 11 of 11. https://enterrsi.si/containment-board/deepseek/ Free to cite under CC BY 4.0 with a link to enterrsi.si. [Rank 10 · D- Alibaba (Qwen)](https://enterrsi.si/containment-board/alibaba/)[Bottom of the board Back to all 11 labs](https://enterrsi.si/containment-board/) Every lab on the board [Anthropic **B+**](https://enterrsi.si/containment-board/anthropic/)[OpenAI **B**](https://enterrsi.si/containment-board/openai/)[Google DeepMind **B-**](https://enterrsi.si/containment-board/google-deepmind/)[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/) 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/)