OpenAI o1 System Card (2024)

OpenAI released the system card for its o1 and o1-mini models on December 21, 2024, detailing safety evaluations, external red teaming, and Preparedness Framework assessments. The models, trained with large-scale reinforcement learning to reason using chain of thought, achieve state-of-the-art performance on benchmarks for risks such as generating illicit advice, stereotyped responses, and jailbreaks, while also introducing heightened risks from increased intelligence.

Computer Science Artificial Intelligence Submitted on 21 Dec 2024 v1 https://arxiv.org/abs/2412.16720v1 , last revised 30 Apr 2026 this version, v2 Title:OpenAI o1 System Card View PDF /pdf/2412.16720 HTML experimental https://arxiv.org/html/2412.16720v2 Abstract:The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. These advanced reasoning capabilities provide new avenues for improving the safety and robustness of our models. In particular, our models can reason about our safety policies in context when responding to potentially unsafe prompts, through deliberative alignment. This leads to state-of-the-art performance on certain benchmarks for risks such as generating illicit advice, choosing stereotyped responses, and succumbing to known jailbreaks. Training models to incorporate a chain of thought before answering has the potential to unlock substantial benefits, while also increasing potential risks that stem from heightened intelligence. Our results underscore the need for building robust alignment methods, extensively stress-testing their efficacy, and maintaining meticulous risk management protocols. This report outlines the safety work carried out for the OpenAI o1 and OpenAI o1-mini models, including safety evaluations, external red teaming, and Preparedness Framework evaluations. Submission history From: Lama Ahmad view email /show-email/7a3f9798/2412.16720 Sat, 21 Dec 2024 18:04:31 UTC 15,258 KB v1 /abs/2412.16720v1 v2 Thu, 30 Apr 2026 02:46:40 UTC 15,260 KB References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .