MiMo-V2.5

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.

MiMo-V2.5-Pro

MiMo-V2.5-Pro is Xiaomi's flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.

MiMo-V2-Pro

MiMo-V2-Pro is Xiaomi's flagship foundation model, featuring over 1T total parameters and a 1M context length, deeply optimized for agentic scenarios. It is highly adaptable to general agent frameworks like OpenClaw. It ranks among the global top tier in the standard PinchBench and ClawBench benchmarks, with perceived performance approaching that of Opus 4.6. MiMo-V2-Pro is designed to serve as the brain of agent systems, orchestrating complex workflows, driving production engineering tasks, and delivering results reliably.

MiMo-V2-Omni

MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimodal perception with agentic capability including visual grounding, multi-step planning, tool use, and code execution, making it well-suited for complex real-world tasks that span modalities.

MiMo-V2.5

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.

MiMo-V2.5-Pro

MiMo-V2.5-Pro is Xiaomi's flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.

MiMo-V2-Pro

MiMo-V2-Pro is Xiaomi's flagship foundation model, featuring over 1T total parameters and a 1M context length, deeply optimized for agentic scenarios. It is highly adaptable to general agent frameworks like OpenClaw. It ranks among the global top tier in the standard PinchBench and ClawBench benchmarks, with perceived performance approaching that of Opus 4.6. MiMo-V2-Pro is designed to serve as the brain of agent systems, orchestrating complex workflows, driving production engineering tasks, and delivering results reliably.

MiMo-V2-Omni

MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimodal perception with agentic capability including visual grounding, multi-step planning, tool use, and code execution, making it well-suited for complex real-world tasks that span modalities.