# LLM Stats

> AI model leaderboard and comparison platform with independent benchmarks, live arenas, and pricing data.

## About
LLM Stats provides independent rankings, benchmarks, and live arena results for AI models including LLMs, image generators, video generators, and audio models. Rankings are based on blind human voting in arenas and standardized benchmark evaluations. Founded by Jonathan Chavez and Sebastian Crossa.

## Leaderboards
- /leaderboards/llm-leaderboard: Overall LLM leaderboard
- /leaderboards/best-ai-for-coding: Best AI models for coding, ranked by arena performance and benchmarks
- /leaderboards/best-ai-for-math: Best AI models for mathematical reasoning
- /leaderboards/best-ai-for-writing: Best AI models for writing and content creation
- /leaderboards/best-ai-for-reasoning: Best AI models for logical reasoning
- /leaderboards/best-ai-for-image-generation: Best AI image generation models
- /leaderboards/best-ai-for-video-generation: Best AI video generation models
- /leaderboards/best-ai-for-search: Best AI models for search and information retrieval
- /leaderboards/best-ai-for-chat: Best AI chat models
- /leaderboards/best-ai-for-tool-calling: Best AI models for function/tool calling
- /leaderboards/best-ai-for-long-context: Best AI models for long document processing
- /leaderboards/best-ai-for-image-understanding: Best AI models for image understanding and OCR
- /leaderboards/best-text-to-speech-ai: Best text-to-speech AI models
- /leaderboards/best-ai-for-transcription: Best AI models for speech-to-text
- /leaderboards/best-ai-for-computer-use: Best AI models for desktop automation
- /leaderboards/best-ai-for-finance: Best AI models for financial analysis
- /leaderboards/best-ai-for-legal: Best AI models for legal tasks
- /leaderboards/best-ai-for-healthcare: Best AI models for healthcare
- /leaderboards/best-ai-for-roleplaying: Best AI models for roleplaying
- /leaderboards/open-llm-leaderboard: Open-source LLM leaderboard

## Models
- /models: AI model catalog with pricing, benchmarks, and specifications
- /models/compare: Side-by-side model comparison tool
- /models/list: Full model listing

## Benchmarks
- /benchmarks: AI model benchmark results and leaderboards
- /benchmarks/all: All benchmark categories

## Arenas
- /arenas: Live blind-voting arenas for AI model evaluation
- /arenas/llm-arena: Text generation arena
- /arenas/coding-arena: Code generation arena
- /arenas/image-arena: Image generation arena
- /arenas/video-arena: Video generation arena
- /arenas/audio-arena: Audio generation arena

## Tools
- /playground: Interactive AI model playground
- /playground/chat: Chat playground
- /playground/code: Code generation playground
- /playground/write: Writing playground
- /playground/imagine: Image generation playground
- /generator/ai-image-generator: AI image generator
- /generator/ai-photo-editor: AI photo editor

## Content
- /blog: Research articles and model launch analyses
- /authors: Author profiles and expertise
- /about-us: About LLM Stats
- /providers: AI model providers
- /organizations: AI organizations and labs

## Data
Rankings update continuously as new arena votes and benchmark results are published. Pricing data is sourced directly from API providers. All benchmark scores are sourced from official model cards and independent reproductions.

## Contact
- Website: https://llm-stats.com
- Twitter/X: https://x.com/LlmStats
- Email: founders@zeroeval.com