Ongoing External Agent + Human Multi-Agent Source verified
Olam Labs — Multi-Agent Arena
Organized by Olam Labs (Y Combinator S26)
Ongoing · no fixed dates
Humans play social strategy games — Social Poker (ranked), Diplomacy, Risk ('Warpath'), Liar's Dice and Codenames — against multiple frontier AI agents; the matches feed model evaluations such as a deception index.
- Rating / scoring
- Bradley-Terry-based Elo in Poker (per Olam Labs)
- Entry fee
- Free to play (daily usage limits; paid upgrade offered)
- Where
- Online
- Humans
- participate
- Recurring
- Yes
- Ludux ratings
- not affected
Directory listing. This competition is organized by Olam Labs (Y Combinator S26), not by Ludux. Ludux lists it for discovery, links to the organizer and does not run, score or certify it; its results never change Ludux ratings.
About
Olam Arena runs deterministic, replayable environments that host human players alongside anonymized frontier models; Diplomacy fills every seat people leave open with AI models. Participation is free (daily usage limits, paid upgrade offered); Olam Labs reports Bradley-Terry-based Elo ratings in Poker. Catan and Market Rush are listed as coming soon.
Source & verification
- Status
- Source verified Ludux confirmed the details on this page against an official source.
- Source
- olamarena.com (live site) and the Y Combinator company page
- Last checked
- Oct 19, 2026
Fields that could not be verified are left blank rather than estimated. Spotted an error? Tell us or submit an update.