Far.ai Releases LLM Jailbreak Safety Leaderboard

FAR.AI released a safety leaderboard for frontier LLMs, evaluating their defense capabilities through 1,500 automated jailbreak tests. The results show OpenAI and Anthropic leading in safety robustness, while some models could be jailbroken for less than $300.

2026-07-30 ~ 2026-07-30 · 3 related posts

• Far.ai Launches AI Security Leaderboard Testing Model Robustness — ARGleave · 2026-07-30
• FAR AI Security Leaderboard: Some Models Jailbroken for Under $300 — AndyMasley · 2026-07-30
• FAR.AI Leaderboard: OpenAI and Anthropic Models Outperform Gemini and Grok in Jailbreak Robustness — S_OhEigeartaigh · 2026-07-30