Xiaomi's MiMo Code: New AI Coding Tool Outperforms Claude Code
Xiaomi's MiMo AI team has open-sourced MiMo Code V0.1.0 , a terminal-native AI coding assistant that the Chinese electronics giant says outperforms Anthropic's Claude Code on key agentic coding benchmarks, especially on long-horizon, multi-step tasks (200+ steps) — at least, according to its own internal beta release and survey of 576 developers. It's also bundling limited-time free access to MiMo-V2.5, its multimodal flagship model with a million-token context window, requir
Xiaomi's AI division has released MiMo Code V0.1.0, an open-source coding assistant designed for terminal use. The company claims this new tool surpasses Anthropic's Claude Code, particularly in handling complex, multi-step coding tasks involving over 200 instructions. These findings are based on internal testing and a survey of 576 developers.
MiMo Code is built upon the OpenCode agent but incorporates Xiaomi's proprietary memory architecture and workflow enhancements. It addresses a common issue with AI coding assistants: memory degradation during extended use. The system utilizes a multi-layered memory approach, including persistent project files and real-time checkpointing by a dedicated sub-agent, to maintain context across sessions.
This development is significant as it introduces a novel approach to AI coding assistants that aims to overcome limitations in maintaining context over long tasks, potentially improving developer productivity.
📌 Kaynak
Bu özet VentureBeat kaynağından otomatik derlenmiştir. Tamamı için orijinal habere gidin.
Orijinal haberi oku →