Pixtral-Large-Instruct-2411, developed by Mistral AI, is a large multimodal model with 124 billion parameters, built on Mistral Large 2. It showcases state-of-the-art image understanding capabilities, capable of interpreting documents, charts, and natural images while maintaining a lead in text comprehension from Mistral Large 2. The model achieves advanced performance on datasets like MathVista, DocVQA, and VQAv2, making it a powerful tool for research and business applications.