CoArena
Public arena and leaderboard that ranks computer-use agents by blind human judgment on real tasks posted by users, with live head-to-head battles, a knowledge-work benchmark, model profiles and published methodology; watching is open to everyone and posting a task or judging needs a sign-in.
What it does
- Evaluation and observability
- Computer use
Features 4
- Live head-to-head battlesTwo agents race the identical task and a human judges the outcome.
- Blind-judged leaderboardComputer-use agents ranked overall and by the kind of work asked.
- Published rulesEvery number is published with the rule that produced it.
- Open to watchWatching needs no account.
Sources
- Pricing
-
Official documentation · 19 Oct 2026
Terms: "Watching Coarena requires nothing." Posting a task or judging a battle requires an account; no paid plan is published.
- Description
-
Official documentation · 19 Oct 2026
Leaderboard page: "Computer-use agents ranked by blind human judgment on real tasks: overall, and by the kind of work asked."
- What it does
-
Official documentation · 19 Oct 2026
Leaderboard page: "Computer-use agents ranked by blind human judgment on real tasks: overall, and by the kind of work asked."
- Sold within
-
Open to watch with no account; a sign-in is needed to post tasks or judge, and no paid plan is published.
- Name
-
Official documentation · 19 Oct 2026
Name as published on the product page.
- URL
-
Official documentation · 19 Oct 2026
Product page, read 2026-10-19.
- Deployment
-
Official documentation · 19 Oct 2026
The pages read state no deployment model beyond the vendor-run service; saas is recorded as the vendor-operated reading.
- Interfaces
-
Official documentation · 19 Oct 2026
The pages read state no deployment model beyond the vendor-run service; saas is recorded as the vendor-operated reading.
Something wrong here? Send a correction — quote this product id: coarena-arena.