FAR AI Launches LLM Security Leaderboard: Many Models Easily Jailbroken

FAR.AI released the AI Security Leaderboard, evaluating LLMs with 1,500 automated jailbreak tests. While OpenAI and Anthropic models led in safety, several other models were easily compromised for under $300.

2026-07-30 ~ 2026-07-31 · 4 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
• FAR.AI Launches AI Security Leaderboard: Most Frontier Models Easily Jailbroken — The Cognitive Revolution · 2026-07-31