# LM Arena

> Web platform for comparing, running, and deploying large language models with hosted inference and API access.

LM Arena provides a web-based environment for running, comparing, and deploying large language models. It focuses on making model evaluation, hosted inference, and simple deployment workflows accessible from a browser and via an API. The platform supports uploading or connecting models, running evaluation workloads, and exposing inference endpoints for applications.

- **Model comparison** *run side-by-side evaluations and benchmarks across models.*
- **Hosted inference** *deploy models to managed endpoints for production usage.*
- **API access** *programmatically invoke models and integrate into applications.*
- **Custom model uploads** *bring your own model artifacts for testing and deployment.*
- **Usage monitoring** *track usage metrics and performance of deployed endpoints.*

To get started, sign up on the web app, upload or connect a model, run a comparison job, and create an inference endpoint; use the provided API keys to integrate inference into your applications.

## Features
- Model comparison
- Hosted inference endpoints
- API access
- Custom model uploads
- Usage monitoring and metrics

## Integrations
Hugging Face, OpenAI, Docker

## Platforms
WEB, API

## Pricing
Open Source

## Links
- Website: https://lmarena.ai
- Documentation: https://help.lmarena.ai/
- Repository: https://github.com/lmarena/lmarena.github.io
- EveryDev.ai: https://www.everydev.ai/tools/lm-arena