Project AURIONAI Use-Cases Research & Innovation
Xiaomi

Xiaomi

Big tech, China. 12 models in the directory.

big techChina
0deployments

Identity

Type
big tech
Country label
China
HQ country
China
Founding country
China
Parent
not in the notes
Parent country
not in the notes
Country basis
the research notes
Where this comes from
Convention D1: a dual label, HQ first, when the HQ, founding or parent country differ.

Models by Class

Models

ModelClassOpennessParametersReleased
XiaomiMiMo-V2.6-Flashmultimodal LLMopen weights permissive309B21 Sep 2026XiaomiMiMo-V2.6-Promultimodal LLMopen weights permissive1.02TSep 2026XiaomiMiMo-V2.5-ProLLMunknown–27 Apr 2026XiaomiMiMo-V2.5multimodal LLMopen weights permissive310B22 Apr 2026XiaomiMiMo-V2-Omnimultimodal LLMproprietary–18 Mar 2026XiaomiMiMo-V2-FlashLLMopen weights permissive309B16 Dec 2025XiaomiDashengaudio classificationopen weights permissive–11 Jun 2024XiaomiMiMoreasoningunknown––XiaomiMiMo-V2.6-Pro distilled Qwen-9B variantLLMunknown9B–XiaomiMiMo-V2.6-Pro-MOPDLLMopen weights permissive––XiaomiMiMo-V2.6-Pro-RLLLMopen weights permissive––XiaomiMiMo-V2-ProLLMunknown––

Scores

BenchmarkModelScoreWho ran itSetting
AIME 2025MiMo-V2-Flash94.1 %vendor-reported
Arena Text leaderboardMiMo-V2.5-Pro1,468 Eloindependent
Arena Text leaderboardMiMo-V2.6-Pro1,480 Eloindependent
Artificial Analysis Intelligence IndexMiMo-V2-Flash22 indexindependentIntelligence Index v4.3.2; marked estimated (asterisk) on page; AA entry MiMo-V2-Flash (Feb 2026)
Artificial Analysis Intelligence IndexMiMo-V2-Omni25 indexindependentIntelligence Index v4.3.2; marked estimated (asterisk) on page; AA entry MiMo-V2-Omni-0327
Artificial Analysis Intelligence IndexMiMo-V2.525 indexindependentIntelligence Index v4.3.2; marked estimated (asterisk) on page
Artificial Analysis Intelligence IndexMiMo-V2.6-Flash38 indexindependentIntelligence Index v4.3.2
Artificial Analysis Intelligence IndexMiMo-V2.6-Pro46 indexindependent
Artificial Analysis Intelligence IndexMiMo-V2.6-Pro46 indexindependent
AutomationBenchMiMo-V2.6-Flash52.3 %vendor-reportedAutomationBench v1.0.6
BrowseCompMiMo-V2-Flash45.4 %vendor-reportedWithout context management
DeepSWEMiMo-V2.6-Flash67.9 %vendor-reported
DeepSWE (version not stated)MiMo-V2.6-Pro71.9 %vendor-reported
GPQA DiamondMiMo-V2-Flash83.7 %vendor-reported
Humanity's Last Exam (HLE)MiMo-V2-Flash22.1 %vendor-reportedNo tools
LiveCodeBenchMiMo-V2-Flash80.6 %vendor-reported
MMLU-ProMiMo-V2-Flash84.9 %vendor-reported
ProgramBenchMiMo-V2.6-Flash26 %vendor-reported
SWE-bench MultilingualMiMo-V2-Flash71.7 %vendor-reported
SWE-bench VerifiedMiMo-V2-Flash73.4 %vendor-reported
SWE-bench VerifiedMiMo-V2-Pro78 %vendor-reported
Terminal-BenchMiMo-V2-Flash38.5 %vendor-reported
Terminal-BenchMiMo-V2.6-Flash87.6 %vendor-reported
Terminal-BenchMiMo-V2.6-Flash28.8 %vendor-reported
Terminal-BenchMiMo-V2.6-Pro89.9 %vendor-reported
ToolathlonMiMo-V2.6-Flash73.6 %vendor-reportedToolathlon-Verified
Where this comes from
Every recorded score of this organisation's models, with who ran it. Scores from different settings are not directly comparable.

Sources

  1. LLM Leaderboard - Comparison of AI models from OpenAI, Anthropic, Google, SpaceXAI & others | Artificial Analysis artificialanalysis.ai https://artificialanalysis.ai/leaderboards/models
  2. huggingface.co/XiaomiMiMo https://huggingface.co/XiaomiMiMo
  3. huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Xiaomi", https://aurion.semai.id/organisations/xiaomi/, records of October 2026.