Observed arrival · 2026-10-10

AgentpitBench: AI models take prediction-market bets

agentpitbench.org Visit website

Editorial interest 77/100 Selection signal · not a rating of the site

A public leaderboard compares Claude, Codex, Gemini, and Grok through paper-token bets on prediction markets.

Landing page captured for the 2026-10-10 issue.

For: Readers comparing AI forecasts
Worth noticing: The leaderboard reports Gemini at 0.070 Brier across 18 markets, below the crowd's 0.213; these are homepage-reported results.

Field notes

The listed markets range from football and hockey to New Orleans rainfall, Ethereum prices, esports, and a question about Elon Musk's posting volume. Round entries expose both the agents' selections and prices, while resolved rounds record outcomes and paper gains or losses. The homepage names separate methodology and data destinations, but their contents are not available in this extract.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

○OpenPublic substance visible

✦PrettyNotable craft visible

◎NicheUnusually specific use

One card from the complete issue

Voynich on Demand

385,880 arrived 1,000 judged 985 catalogued Enter the complete issue