LLM Comparison Frontend 💻

Technologies Getting Started Database Structure Collaborators Contribute

About An open-source LLM comparison tool that allows users to input prompts and compare the performance of language models in a blind test format. It has a wide range of supported models, from opensource ollama ones to the likes of Openai. Simply select two models, then test them across various prompts and scenarios tailored to your domain. Each round provides anonymized responses for evaluation, helping you gain a deeper understanding of each model’s capabilities. All collected data will be published to contribute to open-source research.

📱 Visit this Project

🎨 Layout

💻 Technologies

• React
• Typescript
• TailwindCss

🚀 Getting started

Prerequisites

Here you list all prerequisites necessary for running your project. For example:

• NodeJS
• Git
• [NPM]
• AWS S3 Buckets
• Supabase

Cloning

How to clone your project

git clone https://github.com/Supahands/llm-comparison-frontend

Starting

Before running the server, you should duplicate .env.template and fill in your own environment variables such as AWS S3 and Supabase.

Then, run the development server:

npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun dev

Open http://localhost:3000 with your browser to see the result.

You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.

This project uses next/font to automatically optimize and load Geist, a new font family for Vercel.

💽 Database Structure

The application uses Supabase with the following tables:

available_models

Stores the configuration for available LLM models:

• id: Unique identifier
• provider: The AI provider (e.g., OpenAI, Anthropic)
• model_name: Name of the model (e.g., GPT-4, Claude)
• disabled: Boolean flag to enable/disable models

responses

Collects statistics and responses from model comparisons:

• Stores user choices and model performance metrics
• Used for analyzing model comparison results

⚠️ Disclaimer

Currently, we do not have Anthropic models (Claude) supported on the official site due to API costs. We are actively seeking sponsors to help integrate these models. If you have suggestions for including Anthropic models or would like to sponsor API access, please open an issue on our GitHub repository!

Want to help? Here's what you can do: - Open an issue with suggestions for Anthropic model integration - Reach out about sponsorship opportunities - Share alternative solutions for accessing Anthropic's API

🤝 Collaborators

Special thank you for all people that contributed for this project.

Hank

Wei Ming Thor

Evanz

Noah Rijkaard

📫 Contribute

Here you will explain how other developers can contribute to your project. For example, explaining how can create their branches, which patterns to follow and how to open an pull request

1. git clone https://github.com/Supahands/llm-comparison-frontend
2. git checkout -b feature/NAME
3. Follow commit patterns
4. Open a Pull Request explaining the problem solved or feature made, if exists, append screenshot of visual modifications and wait for the review!

Documentations that might help

📝 How to create a Pull Request

💾 Commit pattern