Benchmark Almanac

FAR.AI

We track 4 benchmarks and 1 arena that FAR.AI made or helped make.

0 in use 3 with public code 2 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
AI Security Leaderboard Models face systematic jailbreak attacks across chemical, biological, radiological, nuclear, explosive and cyber domains. Scores count universal jailbreaks and estimate attacker cost. Jailbreaks and prompt injection Jul 2026 $60 Not in cards
APE (Attempt to Persuade Eval) A model is asked to persuade a simulated user across 600 topics, from benign facts to conspiracies and clearly harmful ones. A judge scores whether it attempts persuasion. Refusing harmful requests Jun 2025 10% Not in cards
ClearHarm Models answer unambiguously harmful CBRN questions. Judges score whether attacks elicit harmful responses from the model. Jailbreaks and prompt injection Jun 2025 Not in cards
TamperBench Open-weight models undergo fine-tuning and representation tampering attacks. Safety and utility metrics measure tamper resistance across attack and model pairs. Jailbreaks and prompt injection Feb 2026 Not in cards

Arenas

Name Kind Released Best score Status
Among Us: A Sandbox for Measuring and Detecting Agentic Deception Language agents play a multiplayer social-deception game with hidden roles. Deception Elo and detection Elo measure success over repeated matches. Multi-agent games Apr 2025 Not in cards