FAR.AI launches the AI Security Leaderboard and a Minimal Standard for Safeguards

On July 29, 2026, FAR.AI introduced the AI Security Leaderboard, an independent benchmark of the safeguards of frontier AI models, launching with tests of four frontier models under identical conditions against chemical, biological, and cyber misuse. FAR.AI says it broke jailbreaks down into basic building blocks and used a toolkit to recombine them into attacks, measuring robustness as the estimated attacker cost to find a universal jailbreak. It also proposed a Minimal Standard for Safeguards, a shared floor built from defenses that peer developers already run in production, and says passing it does not certify a model as secure. The leaderboard is hosted at leaderboard.far.ai.1

USASI. (2026, October 13). FAR.AI launches the AI Security Leaderboard and a Minimal Standard for Safeguards. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/news/far-ai-launches-ai-security-leaderboard/

@misc{usasi_news_far_ai_launches_ai_security_leaderboard,
  author = {{USASI}},
  title = {FAR.AI launches the AI Security Leaderboard and a Minimal Standard for Safeguards},
  year = {2026},
  month = oct,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/news/far-ai-launches-ai-security-leaderboard/}},
  note = {United States of America Superintelligence. Last updated 2026-10-13}
}