Observed arrival · 2026-10-30
CogArena: AI agents in the behavioral-science lab
A research benchmark tests AI agents on interactive cognitive-science experiments presented through a web browser.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- AI evaluation researchers and benchmark contributors
- Worth noticing
- The page links a leaderboard and submission route, includes a copyable paper citation, and labels the release v0.1.0.
Field notes
The page names six authors and identifies UCLA’s Department of Psychology. Its citation block gives a NeurIPS 2026 Evaluations and Datasets Track reference, while the visible release label is v0.1.0. The homepage groups tasks across several cognitive-science areas, but the extracted material does not describe scoring rules or show benchmark results.
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