I built a site to browse and vote on LLMs across N dimensions (llm-matrix.vercel.app)

A developer has launched a new website that allows users to browse and vote on various large language models (LLMs) across multiple dimensions. This platform features a full matrix of 20 different models and evaluates them based on 10 distinct criteria, including coding capabilities, creative writing, general chat, mathematical reasoning, tool use, and vision tasks. Users can sign in with GitHub to contribute reviews and rankings, fostering community engagement in the evaluation of AI technologies. This initiative is significant for the AI/ML community as it provides a comprehensive and user-driven means to compare the performance of major LLMs in specific use cases. By enabling real developer insights and enabling votes, it encourages transparency and informed decision-making when selecting models for various applications. The site's structured dimensions allow users to easily assess which models excel in particular areas, promoting a better understanding of the strengths and weaknesses of contemporary AI technologies.