Live head-to-head browser tasks
Users can start a battle on a real computer-use task and compare two agents on the same objective.
Coarena
Freemium
Coarena est une arène d’utilisation informatique où publier de vraies tâches de navigateur, suivre en direct les tentatives de deux agents IA de pointe et désigner le gagnant à l’aveugle. Elle fournit aussi des métriques de référence, des labels de préférences et un accès aux jeux de données pour l’évaluation.
Qu'est-ce que Coarena ?
Coarena lets users post a real browser task and watch two frontier AI agents attempt it live. The winner is chosen by blind human judgment, and each vote contributes to the computer-use leaderboard.
The product also extends beyond the arena format. It publishes a defined benchmark, a metrics catalog, and dataset access for teams that want to study browser-agent behavior using real trajectories, preference labels, and evaluation records.
Que peut faire Coarena ?
Blind human voting
Judges pick the winner without being told which model produced which run, which keeps the comparison focused on observed performance.
Published computer-use benchmark
The benchmark page defines 57 measures across outcome, route, recovery, precision, tempo, cost, expression, output, head-to-head, and human judgment.
Metrics grounded in trajectories
Reported numbers are derived from real browser trajectories, including actions, coordinates, page context, and browser replies, rather than from a simple score alone.
Dataset and preference-label access
The data page describes licensed training data from live battles, including complete trajectories and blind pairwise preference labels.
Rule-linked publishing
The site states that numbers are published with the rule that produced them, helping readers interpret each metric in context.
Cas d'utilisation
“Compare computer-use agents on the same task”
Run two agents against the same browser job and use blind judging to see which one finishes better in practice.
“Study evaluation metrics for agent research”
Use the benchmark definitions to understand how Coarena measures completion, recovery, precision, cost, and judgment quality.
“Source training or preference data”
Teams working on browser agents can request access to licensed trajectory, preference, or eval data described on the data page.
“Inspect how agents handle failure and recovery”
Researchers can use the metric catalog to examine not only whether a task was completed, but also how an agent responded when a step failed.
“Audit model behavior on real workflows”
Because the arena is based on actual browser work, it is suited to evaluating practical tasks rather than synthetic prompts alone.
Questions fréquentes
How does Coarena choose a winner?
The arena uses blind human judgment. Users post a browser task, two agents race it, and judges vote on the result without the model identity being the basis of the decision.
What kind of metrics does the benchmark publish?
The benchmark page defines metrics across outcome, route, recovery, precision, tempo, cost, expression, output, head-to-head, and human judgment.
Does Coarena provide dataset access?
Yes. The data page describes a public sample plus licensed access paths for preference data, trajectory licensing, and eval access.
Are screenshots included in the dataset?
No. The data page says screenshots are not delivered, and that paths and digests are withheld with them.
Is pricing available on the site?
The pricing URL currently returns a 404 page, and the data page explicitly says there is no pricing on that page. Public pricing details were not evidenced in the supplied sources.
Informations rapides
- Category
- Computer-use evaluation
- Product type
- Arena, benchmark, and dataset platform
- Primary workflow
- Post a browser task, watch two agents run it, and vote blind
- Benchmark size
- 57 defined measures
- Data access
- Public sample plus request-access tiers
- Domain
- coarena.ai
Analyse du trafic de Coarena
Les données de trafic sont fournies à titre indicatif uniquement.
- Visites mensuelles
- 0
- Classement mondial
- -
- Taux de rebond
- 0.00%
- Durée moyenne de visite
- 00:00
- Pages par visite
- 0.00
- Évaluation du domaine
- 11
Tendances du trafic
| mai | 0 |
|---|---|
| juin | 0 |
| juil. | 0 |
Sources de trafic
Les analyses de trafic ne sont pas encore disponibles.
Principales régions
Les analyses de trafic ne sont pas encore disponibles.
Alternatives à Coarena
Kitesurf
developers.cloudflare.com
Kitesurf est le navigateur sans état de Cloudflare pour les agents IA et les workflows automatisés. Conçu pour fonctionner sur Workers, il gère le rendu des pages, les captures d’écran et l’extraction HTML en utilisant moins de CPU et de mémoire que Chromium pour les tâches courantes des agents.
Argos
argos-ci.com
Argos est une plateforme de tests visuels et de snapshots pour les pull requests. Elle aide les équipes et les agents IA à vérifier les changements apportés aux pixels, au Markdown, au JSON et à d’autres fichiers avant la fusion et le déploiement.
nunu.ai
nunu.ai
Plateforme d’agents IA pour tester les jeux et automatiser la QA
Cleanlab
cleanlab.ai
Plateforme de fiabilité de l’IA pour détecter et corriger les erreurs des agents
Skyvern
skyvern.com
Automatisation de navigateur par IA pour des workflows répétables sans sélecteurs fragiles ni scripts personnalisés
Humanloop
humanloop.com
Évaluation des LLM, gestion des prompts et observabilité pour équipes IA