MiniMax has announced the launch of its latest language model, MiniMax-M2.5, targeting developers, enterprises, and professionals who require advanced coding, agentic automation, and office productivity capabilities. The model is publicly available through the MiniMax platform, with two versions, M2.5 and M2.5-Lightning, offering throughput options of 50 and 100 tokens per second, respectively. The model can be accessed via API and is integrated into the MiniMax Agent product.
MiniMax-M2.5 builds on substantial advancements over previous versions, particularly in coding proficiency, multilingual programming, and agentic task automation. It supports over 10 programming languages and is trained using reinforcement learning across hundreds of thousands of real-world environments. The model demonstrates state-of-the-art results on industry benchmarks like SWE-Bench Verified and BrowseComp, and provides full-stack development support from system design to code review. In office scenarios, M2.5 leverages standardized Office Skills for tasks in Word, PowerPoint, and Excel, with domain-specific customization available. Its cost structure undercuts leading competitors, making continuous operation much more economical.
MiniMax, the company behind M2.5, leverages its proprietary RL framework, Forge, and advanced infrastructure to rapidly iterate its model series. The firm has involved senior professionals from finance, law, and social sciences in training data curation, ensuring the outputs meet real-world business requirements. Early internal adoption has seen widespread use across company operations, with M2.5-generated code comprising the majority of new software commits.
