# Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment Evaluation

arXiv: https://arxiv.org/abs/2501.17749 · HTML: https://mlsanity.com/paper/2501.17749/

## Key facts

- Cited by 13 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 18 of its 25 references that are in the map.
- First posted on arXiv 29 Jan 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 18 of 18)

- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation](https://mlsanity.com/paper/2310.06987/) (2023)
- [A StrongREJECT for Empty Jailbreaks](https://mlsanity.com/paper/2402.10260/) (2024)
- [SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal](https://mlsanity.com/paper/2406.14598/) (2024)
- [SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models](https://mlsanity.com/paper/2402.05044/) (2024)
- [SafetyBench: Evaluating the Safety of Large Language Models](https://mlsanity.com/paper/2309.07045/) (2023)
- [SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models](https://mlsanity.com/paper/2311.08370/) (2023)
- [SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models](https://mlsanity.com/paper/2410.18927/) (2024)
- [ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors](https://mlsanity.com/paper/2402.16444/) (2024)
- [S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models](https://mlsanity.com/paper/2405.14191/) (2024)
- [Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models](https://mlsanity.com/paper/2408.15313/) (2024)
- [WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models](https://mlsanity.com/paper/2408.03837/) (2024)
- [CHiSafetyBench: A Chinese Hierarchical Safety Benchmark for Large Language Models](https://mlsanity.com/paper/2406.10311/) (2024)
- [LongSafety: Enhance Safety for Long-Context LLMs](https://mlsanity.com/paper/2411.06899/) (2024)

## Built on by (most cited first, 13 of 13)

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning](https://mlsanity.com/paper/2503.07065/) (2025)
- [Safety in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2504.17704/) (2025)
- [o3-mini vs DeepSeek-R1: Which One is Safer?](https://mlsanity.com/paper/2501.18438/) (2025)
- [Large Reasoning Models Learn Better Alignment from Flawed Thinking](https://mlsanity.com/paper/2510.00938/) (2025)
- [Dyve: Thinking Fast and Slow for Dynamic Process Verification](https://mlsanity.com/paper/2502.11157/) (2025)
- [Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approach](https://mlsanity.com/paper/2503.10573/) (2025)
- [Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models](https://mlsanity.com/paper/2505.19690/) (2025)
- [When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models](https://mlsanity.com/paper/2510.21285/) (2025)
- [Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Ability](https://mlsanity.com/paper/2512.01848/) (2025)
- [ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models](https://mlsanity.com/paper/2606.23404/) (2026)
- [Evaluating Large Language Models on the Spanish Medical Intern Resident (MIR) Examination 2024/2025:A Comparative Analysis of Clinical Reasoning and Knowledge Application](https://mlsanity.com/paper/2503.00025/) (2025)
- [Reasoning without Regret](https://mlsanity.com/paper/2504.09777/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) have become an integral part of our daily lives. However, they impose certain risks, including those that can harm individuals' privacy, perpetuate biases and spread misinformation. These risks highlight the need for robust safety mechanisms, ethical guidelines, and thorough testing to ensure their responsible deployment. Safety of LLMs is a key property that needs to be thoroughly tested prior the model to be deployed and accessible to the general users. This paper reports the external safety testing experience conducted by researchers from Mondragon University and University of Seville on OpenAI's new o3-mini LLM as part of OpenAI's early access for safety testing program. In particular, we apply our tool, ASTRAL, to automatically and systematically generate up to date unsafe test inputs (i.e., prompts) that helps us test and assess different safety categories of LLMs. We automatically generate and execute a total of 10,080 unsafe test input on a early o3-mini beta version. After manually verifying the test cases classified as unsafe by ASTRAL, we identify a total of 87 actual instances of unsafe LLM behavior. We highlight key insights and findings uncovered during the pre-deployment external testing phase of OpenAI's latest LLM.