One of the best is LLM Explorer. It catalogs a huge collection of open-source Large Language Models (LLMs) and Small Language Models (SLMs) in a variety of ways, including size, benchmark scores and memory usage. It's got categorized lists, benchmarks, analytics and detailed model descriptions so you can easily compare and pick the best models for your needs. It also tracks trending models so you can keep up with what's new.
Another good option is Contentable. It lets you compare, test, build and deploy low-code AI models from top providers like Open AI, Google and Llama. It's got side-by-side model comparison, real-time collaboration and visual workflow design with no code required, so it's good for teams or individuals who want to pick the best AI models and get them into production more easily. You can quickly deploy and share AI models, prototype and make decisions by comparing different models and their results.
GMTech is another good option. It aggregates a range of AI language models and image generators from top providers like OpenAI, Google and Meta. The Comparison Lab lets you compare models side by side, the Chat Lab lets you switch models in the middle of a conversation, and image generation tools let you generate images from text prompts. It's a good all-purpose option for anyone who wants to experiment and integrate multiple AI models into their workflow.