Non finito is a comprehensive platform designed to facilitate the comparison and evaluation of multimodal models, enabling users to assess various AI models' performance across diverse tasks. It offers a suite of tools and features that allow for in-depth analysis and benchmarking, catering to both researchers and practitioners in the field of artificial intelligence. Key Features and Functionality: - Model Comparison: Users can compare multiple multimodal models side by side, evaluating their outputs on identical inputs to discern performance differences. - Public Evaluations: Access to a repository of public evaluations allows users to review existing assessments and gain insights into model capabilities. - Custom Evaluations: Registered users have the ability to create and manage their own evaluations, tailoring assessments to specific needs and criteria. - Diverse Evaluation Examples: The platform provides a range of example evaluations, including tasks like entity tracking, logical reasoning, real-world question answering, visual deductive reasoning, and more, showcasing the versatility of the models. Primary Value and User Solutions: Non finito addresses the need for a centralized, user-friendly platform where AI models can be systematically evaluated and compared. By offering tools for both public and custom evaluations, it empowers users to make informed decisions about model selection and application. The platform's emphasis on multimodal evaluations ensures that users can assess models' performance across various data types and tasks, enhancing the development and deployment of AI solutions.