MiMo V2 Pro
Xiaomi's flagship 1T-parameter model deeply optimized for agentic scenarios. 1M-token context with performance approaching Opus 4.6 on standard benchmarks. Designed as the brain of agent systems — orchestrating complex workflows, coding, and production engineering tasks.
Benchmarks
This model hasn't been evaluated by Artificial Analysis yet. Benchmark scores will appear once they're published.
Specifications
Providers
Compare with
Frequently Asked Questions about MiMo V2 Pro▼
Who created MiMo V2 Pro?
▼
MiMo V2 Pro was created by Xiaomi.
Is MiMo V2 Pro a reasoning model?
▼
No, MiMo V2 Pro is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.
Does MiMo V2 Pro support image or vision input?
▼
No, MiMo V2 Pro does not currently support image or vision input. It is a text-only model.
Does MiMo V2 Pro support audio?
▼
No, MiMo V2 Pro does not support audio input.
Is MiMo V2 Pro open source?
▼
MiMo V2 Pro is a proprietary model developed by Xiaomi. The model weights and training data are not publicly available.
Where can I use MiMo V2 Pro?
▼
You can chat with MiMo V2 Pro on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access MiMo V2 Pro through Xiaomi's own API or platform.