SiteList review score
Built on a modern Next.js foundation optimized for AI search. Dragged down by homepage rendering defects and missing formal developer documentation.
Reviewed on Aug 15, 2026
Coarena by Coasty — The arena where agents battle on real-world work
coarena.ai
Unclaimed listingWhat it does
Platform for live computer-use agent evaluations where users post browser tasks, watch two AI agents race, and judge outputs blind to update a public leaderboard.
Two ratings
Verified user rating
—
No verified reviews yet — the evidence locker is empty.
Screenshots
Captured during our latest review on Aug 24, 2026
Pricing details
No paid tiers, usage-based pricing, or enterprise contact information evidenced on the homepage or navigation. Billed monthly.
View sourceKey features
Live Agent Race
Evaluation
Posts a real browser task and watches two frontier AI agents complete it simultaneously.
Blind Human Judging
Evaluation
Users evaluate agent outputs without knowing which model produced them, with votes updating a public ranking.
Computer-Use Leaderboard
Benchmarking
Publishes real-world evaluation metrics and rankings for computer-use AI agents based on live tasks.
Integrations
Google
Buyer questions
Questions buyers actually ask
What is Coarena?
Coarena is an AI agent evaluation platform focused on computer-use agents. It provides a live leaderboard and public datasets to benchmark how agents perform on real-world browser-based tasks.
Is the Coarena benchmark trustworthy?
Yes, the site establishes high credibility by citing source code for neutrality and avoiding common marketing clichés. It is backed by Coasty Systems and Y Combinator.
What are the main technical issues with Coarena?
The site suffers from a 2MB+ homepage payload and render-blocking resources. Additionally, it has accessibility flaws like 10px typography and mobile content clipping.
Does Coarena offer developer documentation?
Currently, Coarena lacks a formal documentation surface. While it provides high-level governance and an llms.txt file, there is no comprehensive self-serve help for developers.
How does Coarena handle AI search engines?
Coarena is highly optimized for AI search (AEO). It uses 100% server-rendered content and provides a robust llms.txt file, making its data easily extractable by answer engines and researchers.
Answers are based on SiteList's latest evidence review. Read the full review.
The expert review
Coarena scores 80/100, distinguishing itself with high-conviction technical positioning and a modern Next.js foundation optimized for AI search. Its most material weaknesses are critical homepage rendering defects and a lack of formal developer documentation.
80/100: strong technical foundation with fixable UX hurdles
Verified user reviews
0 verifiedNo reviews yet. The evidence locker is empty.
Reviews from verified users appear here once approved.
Reviews are from the SiteList community. Some reviewers received incentives — disclosed in the review, always. The verdict is never for sale.
Scores across 13 dimensions
Brand & experience
Performance
Content & editorial
Trust & decision surfaces
Search & discoverability
Docs & measurement
- Domain
- coarena.ai
- Category
- Monitoring & observability
- Pricing
- Free · $0/mo
- Platforms
- web
- Last checked
- Aug 15, 2026
- Public dimensions
- 13
Similar tools
Home
Metrician screenshot 1 of 4: Home
Metrician
Score 88 out of 100 — Strongmetrician.io
Metrician is a Chrome extension that displays AI usage limits, usage pace, and reset times for ChatGPT, Claude, Grok, OpenCode Go, and Ollama inside a customizable floating browser widget.
Home
qsa.sh — External security scan of your own IP, in your terminal screenshot 1 of 4: Home
qsa.sh — External security scan of your own IP, in your terminal
Score 86 out of 100 — Strongqsa.sh
A terminal-based service that performs an external port and vulnerability scan of the user's own public IP address using open-source tools (naabu, nmap, nuclei), offering a free live-streaming tier and paid async/deep scan tiers.
Home
CodeBurn — See where your AI coding spend actually goes screenshot 1 of 4: Home
CodeBurn — See where your AI coding spend actually goes
Score 84 out of 100 — Strongcodeburn.app
CodeBurn is a free, open-source, local-first tool that tracks AI coding token usage and cost across dozens of developer tools. It breaks down spend by model, project, and task using session files already on the user's disk, with no data uploaded.
Home
Fixvibe screenshot 1 of 4: Home
Fixvibe
Score 83 out of 100 — Strongfixvibe.app
Security scanner for AI-generated web apps, including DAST, BaaS misconfiguration checks, leaked-secret detection, and AI-ready remediation prompts.