MiMo
Xiaomi's Open Source Model, Born for Reasoning
349 followers
Xiaomi's Open Source Model, Born for Reasoning
349 followers
Open-source (Apache 2.0) LLM series 'born for reasoning.' Pre-trained & RL-tuned models (like the 7B) match o1-mini on math/code. Base/SFT/RL models released.
This is the 5th launch from MiMo. View more
MiMo-V2.5 & Pro
Launching today
The Xiaomi MiMo-V2.5 series introduces V2.5-Pro for complex, long-horizon software engineering and V2.5 for highly efficient, native omnimodal understanding. Both models match frontier performance while drastically reducing token consumption.
Free Options
Launch Team
Flowtica Scribe
Hi everyone!
Xiaomi MiMo ships new models at a pace that’s honestly astonishing. MiMo-V2.5-Pro is their strongest yet — big jumps in agentic coding, long-horizon tasks, and real-world reliability. The lighter V2.5 brings native multimodal (image/audio/video) on top of that while staying very token-efficient.
MiMo is clearly accelerating to become one of the fastest-moving players in the frontier tier.
Right now you can try it in MiMo Studio and use the whole series through their Token Plan, and the models will be open-sourced soon!