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 es un arena de uso informático donde puedes publicar tareas reales de navegador, ver en directo cómo dos agentes de IA de vanguardia intentan resolverlas y juzgar a ciegas quién gana. También ofrece métricas de referencia, etiquetas de preferencias y acceso a conjuntos de datos para evaluar el uso informático.
¿Qué es 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.
¿Qué puede hacer 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.
Casos de uso
“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.
Preguntas frecuentes
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.
Datos rápidos
- 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
Análisis de tráfico de Coarena
Los datos de tráfico son solo como referencia.
- Visitas mensuales
- 0
- Clasificación global
- -
- Tasa de rebote
- 0.00%
- Duración media de la visita
- 00:00
- Páginas por visita
- 0.00
- Valoración del dominio
- 11
Tendencias de tráfico
| may | 0 |
|---|---|
| jun | 0 |
| jul | 0 |
Fuentes de tráfico
Las analíticas de tráfico aún no están disponibles.
Principales regiones
Las analíticas de tráfico aún no están disponibles.
Alternativas a Coarena
Kitesurf
developers.cloudflare.com
Kitesurf es el navegador sin estado de Cloudflare para agentes de IA y flujos de trabajo automatizados. Diseñado para ejecutarse en Workers, renderiza páginas, captura pantallas y extrae HTML con menos CPU y memoria que Chromium en tareas habituales de agentes.
nunu.ai
nunu.ai
Plataforma de agentes de IA para automatizar pruebas de juegos y flujos de control de calidad mediante tareas de extremo a extremo en dispositivos reales, con paneles e informes para revisar los resultados.
Ragas
ragas.io
Marco de código abierto para probar y evaluar aplicaciones de LLM, generar datos sintéticos de evaluación, medir su calidad y supervisar su comportamiento en producción.
FetchSandbox
fetchsandbox.com
FetchSandbox es una herramienta para probar integraciones de API, webhooks y flujos de trabajo con estado desde entornos de programación con IA. Permite a desarrolladores y agentes validar integraciones sin usar claves API reales ni consumir la cuota de producción.
Plurai
plurai.ai
Plurai es una plataforma de confianza para agentes de IA que permite simular, evaluar y aplicar medidas de protección, para probar agentes en producción, supervisar su comportamiento y protegerlos en tiempo real antes y después del despliegue.
NovaSynth
noveum.ai
Plataforma de pruebas de preproducción para agentes de IA que simula usuarios en llamadas SIP reales, audio de LiveKit y chat para ensayar conversaciones, detectar fallos y validar correcciones antes del lanzamiento.