Social Arena launches a human-vs-AI benchmark built on Risk, Catan and Poker

mattbeane · x · 2026-07-21

Social Arena introduces human-vs-AI social games for behavioral evaluation

OlaM Labs is releasing Social Arena, a platform where humans play social games such as Risk, Catan, and Poker against AI agents.

The first benchmark is the Deception Index, and the system uses these multi-agent matches to evaluate model behavior in imperfect-information, multi-turn settings. The poster calls it a promising revival of one of the classic proving grounds for AI.

Related event: YC's Social Arena Tests AI Deception in Social Games(3 posts)→

Original post →

More from Fun

Fun channel →