Nux - Ai Leaderboard

Discover, compare and use the world’s top large language models (LLMs) in one app. With NUX you get access to a dynamically updated leaderboard of models from major providers and open-source communities alike — then tap into them directly for experimentation, testing or production-use. Track model performance, explore key metrics, and pick the right LLM for your needs.
Why NUX is different
Explore a full LLM leaderboard ranking models from providers like OpenAI (GPT-5 GPT-Codex, Anthropic (Claude, Opus), Grok, and dozens of open-source models such as Llama 2, Mistral, Falcon, Vicuna, Deepseek and more.
Every model that supports API access is listed — from brand-name models to smaller, cutting-edge open-source variants.
Full access: switch between models, test prompts, evaluate responses and compare quality, speed and cost in real-time.
Get detailed model metadata: parameters, training data, supported features, typical use-cases and API endpoint details.
Build custom workflows: use any model directly in the app, save your favourite models, track your experiments, and switch seamlessly.
Stay up to date: new models and providers are added continuously, keeping you on the frontier of LLM innovation.
Ideal for developers, AI researchers, product teams, and curious users who want to explore and deploy large language models.
Key features
Leaderboard view ranking LLMs by performance metrics (accuracy, cost-efficiency, speed) and user ratings.
Filter and search across hundreds of models: major brands (OpenAI, Anthropic, Grok) and open source models (Llama 2, Mistral, Falcon, Vicuna, StableLM, OpenAssistant, Deepseek, Kimi k2, Qwen).
In-app access to the API endpoints for each model — send prompts, receive responses, and test capabilities without leaving the app.
Comparison mode: pick two or more models and run the same prompt across them side-by-side to see how they differ.
“My Experiments” workspace: track your prompt history, favourite models, and saved responses.
Cost monitoring and usage stats: keep an eye on your API calls, tokens used, and get alerts on high usage.
Model update notifications: when new versions become available, get notified and re-run your tests easily.
Designed for both power-users and beginners: a clean interface, helpful tooltips and context-aware prompts.
Use-cases
Developer building the best model for a chatbot or virtual assis