mlsanityData to 14 Oct 2026

o3-mini vs DeepSeek-R1: Which One is Safer?

arXiv 2501.18438 ↗First posted 30 Jan 2025cs.SE cs.AIcited by 24

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

The irruption of DeepSeek-R1 constitutes a turning point for the AI industry in general and the LLMs in particular. Its capabilities have demonstrated outstanding performance in several tasks, including creative thinking, code generation, maths and automated program repair, at apparently lower execution cost. However, LLMs must adhere to an important qualitative property, i.e., their alignment with safety and human values. A clear competitor of DeepSeek-R1 is its American counterpart, OpenAI's o3-mini model, which is expected to set high standards in terms of performance, safety and cost. In this technical report, we systematically assess the safety level of both DeepSeek-R1 (70b version) and OpenAI's o3-mini (beta version). To this end, we make use of our recently released automated safety testing tool, named ASTRAL. By leveraging this tool, we automatically and systematically generated and executed 1,260 test inputs on both models. After conducting a semi-automated assessment of the outcomes provided by both LLMs, the results indicate that DeepSeek-R1 produces significantly more unsafe responses (12%) than OpenAI's o3-mini (1.2%).

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 22 of its 30 references that are in the map. First posted on arXiv 30 Jan 2025.

Builds on

22 of 30 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment Evaluation29 Jan

Other references · 21

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  3. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  4. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,429
  5. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,207
  6. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 860
  7. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 729
  8. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Modelscited by 489
  9. 2023Catastrophic Jailbreak of Open-source LLMs via Exploiting Generationcited by 451
  10. 2024A StrongREJECT for Empty Jailbreakscited by 385
  11. 2024SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusalcited by 240
  12. 2024SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Modelscited by 228
9 more
  1. 2023SafetyBench: Evaluating the Safety of Large Language Modelscited by 199
  2. 2023SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Modelscited by 76
  3. 2024SafeBench: A Safety Evaluation Framework for Multimodal Large Language Modelscited by 69
  4. 2024ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectorscited by 51
  5. 2024S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Modelscited by 33
  6. 2024WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Modelscited by 17
  7. 2024CHiSafetyBench: A Chinese Hierarchical Safety Benchmark for Large Language Modelscited by 15
  8. 2024LongSafety: Enhance Safety for Long-Context LLMscited by 11
  9. 2025ASTRAL: Automated Safety Testing of Large Language Modelscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 22; 2026: 2.

24 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  2. 2025Safety in Large Reasoning Models: A Surveycited by 64
  3. 2025100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Modelscited by 30
  4. 2025SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Modelscited by 29
  5. 2025Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findingscited by 27
  6. 2025To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Modelscited by 22
  7. 2025Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilitiescited by 20
  8. 2025A Comparison of DeepSeek and Other LLMscited by 10
  9. 2025Safety Evaluation of DeepSeek Models in Chinese Contextscited by 9
  10. 2025Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?cited by 9
  11. 2025Thinking Preference Optimizationcited by 8
  12. 2025Dynamic Chain-of-Thought: Towards Adaptive Deep Reasoningcited by 5
12 more
  1. 2026When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoningcited by 5
  2. 2025Policy Frameworks for Transparent Chain-of-Thought Reasoning in Large Language Modelscited by 4
  3. 2025Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language Modelscited by 4
  4. 2025AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Modelscited by 4
  5. 2025LLMs in Disease Diagnosis: A Comparative Study of DeepSeek-R1 and O3 Mini Across Chronic Health Conditionscited by 3
  6. 2025Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategycited by 3
  7. 2026How Does the Thinking Step Influence Model Safety? An Entropy-based Safety Reminder for LRMscited by 3
  8. 2025Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Abilitycited by 2
  9. 2025RRTL: Red Teaming Reasoning Large Language Models in Tool Learningcited by 1
  10. 2025Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Datacited by 0
  11. 2025Efficient Strategy for Improving Large Language Model (LLM) Capabilitiescited by 0
  12. 2025RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Safety Evaluation and Enhancement of DeepSeek Models in Chinese Contexts
  2. 2025DeepSeek in Healthcare: A Survey of Capabilities, Risks, and Clinical Applications of Open-Source Large Language Models
  3. 2025RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability
  4. 2025The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1
  5. 2024OpenAI o1 System Card
  6. 2025Brief analysis of DeepSeek R1 and its implications for Generative AI
  7. 2025DeepSeek-R1 Outperforms Gemini 2.0 Pro, OpenAI o1, and o3-mini in Bilingual Complex Ophthalmology Reasoning
  8. 2026DeepSight: An All-in-One LM Safety Toolkit