An Introduction to AI Secure LLM Safety Leaderboard

AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems

Bringing the Artificial Analysis LLM Performance Leaderboard to Hugging Face

Open LLM Leaderboard: DROP deep dive

Online Safety Monitoring for LLMs

arXiv:2607. 02510v1 Announce Type: new Abstract: Despite alignment training, LLMs remain prone to generating unsafe outputs at deployment time.

Introducing the Open FinLLM Leaderboard

Democratizing AI Safety with RiskRubric.ai

Introducing the Open Leaderboard for Japanese LLMs!

Fixing Open LLM Leaderboard with Math-Verify

Operator System Card

Drawing from OpenAI’s established safety frameworks, this document highlights our multi-layered approach, including model and product mitigations we’ve implemented to protect against prompt engineering and jailbreaks, protect privacy and security, as well as details our external red teaming efforts, safety evaluations, and ongoing work to further refine these safeguards.

LLM agent safety, multi-turn red-teaming, jailbreak benchmarks, adversarial robustness, safety-critical systems

arXiv:2606. 20408v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized.

Our approach to AI safety

Ensuring that AI systems are built, deployed, and used safely is critical to our mission.

Introducing the Open Arabic LLM Leaderboard