# AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons

arXiv: https://arxiv.org/abs/2503.05731 · HTML: https://mlsanity.com/paper/2503.05731/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2025.

## Built on by (most cited first, 30 of 35)

- [Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models](https://mlsanity.com/paper/2511.15304/) (2025)
- [Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking](https://mlsanity.com/paper/2604.11581/) (2026)
- [MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.20824/) (2025)
- [D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models](https://mlsanity.com/paper/2509.17938/) (2025)
- [SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning](https://mlsanity.com/paper/2606.22873/) (2026)
- [Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation](https://mlsanity.com/paper/2509.14760/) (2025)
- [Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting](https://mlsanity.com/paper/2606.09809/) (2026)
- [The Trust Fabric: Decentralized Interoperability and Economic Coordination for the Agentic Web](https://mlsanity.com/paper/2507.07901/) (2025)
- [Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models](https://mlsanity.com/paper/2508.01554/) (2025)
- [Detecting and Preventing Harmful Behaviors in AI Companions: Development and Evaluation of the SHIELD Supervisory System](https://mlsanity.com/paper/2510.15891/) (2025)
- [Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety](https://mlsanity.com/paper/2604.18487/) (2026)
- [Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety](https://mlsanity.com/paper/2605.22643/) (2026)
- [FedMM-X: A Trustworthy and Interpretable Framework for Federated Multi-Modal Learning in Dynamic Environments](https://mlsanity.com/paper/2503.19564/) (2025)
- [ExpGuard: LLM Content Moderation in Specialized Domains](https://mlsanity.com/paper/2603.02588/) (2026)
- [Contemplative Artificial Intelligence](https://mlsanity.com/paper/2504.15125/) (2025)
- [Phare: A Safety Probe for Large Language Models](https://mlsanity.com/paper/2505.11365/) (2025)
- [Decoding Federated Learning: The FedNAM+ Conformal Revolution](https://mlsanity.com/paper/2506.17872/) (2025)
- [When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels](https://mlsanity.com/paper/2605.06652/) (2026)
- [FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming](https://mlsanity.com/paper/2606.19887/) (2026)
- [HarmProfile: Characterizing Harmful Distributions in Frontier LLMs](https://mlsanity.com/paper/2608.14577/) (2026)
- [Deprecating Benchmarks: Criteria and Framework](https://mlsanity.com/paper/2507.06434/) (2025)
- [Inducing Epistemological Humility in Large Language Models: A Targeted SFT Approach to Reducing Hallucination](https://mlsanity.com/paper/2603.17504/) (2026)
- [Retrieval with Multiple Query Vectors through Anomalous Pattern Detection](https://mlsanity.com/paper/2605.01965/) (2026)
- [Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models](https://mlsanity.com/paper/2605.06213/) (2026)
- [StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs](https://mlsanity.com/paper/2605.10442/) (2026)
- [Metaphor Is Not All Attention Needs](https://mlsanity.com/paper/2605.12128/) (2026)
- [From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI](https://mlsanity.com/paper/2605.16471/) (2026)
- [Pluralis v0.1: Towards a Multicultural, Multimodal, Multilingual Benchmark for AI Risk and Reliability](https://mlsanity.com/paper/2607.06196/) (2026)
- [The Human Utility Factor: A Computable Welfare Metric That Reframes AI Governance as a Constrained Optimisation Problem](https://mlsanity.com/paper/2607.26068/) (2026)
- [Fool's Gold: Defensive Deception Against Safety-Removal Attacks on Open-Weight Models](https://mlsanity.com/paper/2608.17202/) (2026)

## Abstract (arXiv)

The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product risk and reliability. Its development employed an open process that included participants from multiple fields. The benchmark evaluates an AI system's resistance to prompts designed to elicit dangerous, illegal, or undesirable behavior in 12 hazard categories, including violent crimes, nonviolent crimes, sex-related crimes, child sexual exploitation, indiscriminate weapons, suicide and self-harm, intellectual property, privacy, defamation, hate, sexual content, and specialized advice (election, financial, health, legal). Our method incorporates a complete assessment standard, extensive prompt datasets, a novel evaluation framework, a grading and reporting system, and the technical as well as organizational infrastructure for long-term support and evolution. In particular, the benchmark employs an understandable five-tier grading scale (Poor to Excellent) and incorporates an innovative entropy-based system-response evaluation. In addition to unveiling the benchmark, this report also identifies limitations of our method and of building safety benchmarks generally, including evaluator uncertainty and the constraints of single-turn interactions. This work represents a crucial step toward establishing global standards for AI risk and reliability evaluation while acknowledging the need for continued development in areas such as multiturn interactions, multimodal understanding, coverage of additional languages, and emerging hazard categories. Our findings provide valuable insights for model developers, system integrators, and policymakers working to promote safer AI deployment.