Xiaomi · MoE Architecture
MiMo-V2-Pro
Trillion-parameter foundation model (1T total, 42B active) optimized for agentic workloads with 1M-token context and hybrid attention. Ranks #2 among Chinese LLMs and #8 globally; achieves #3 on PinchBench (81.0) and coding performance approaching Claude Opus 4.6.
Open the source ↗Similar Language Models releases
- Groot-280B-A16B-261023
GrootTeam · Open reasoning MoE · Week 45, 2026
- Apex-35B-V1.0
Apex Intelligence · Research automation LLM · Week 45, 2026
- Ling-3.0-flash-Sante
inclusionAI (Ant Group) · Medical LLM · Week 44, 2026
- Kimi K3.1 Pro
Moonshot AI · Open-Weight Frontier · Week 44, 2026
- DeepSeek-V4.1-Flash-1017
DeepSeek · Open-Weight LLM · Week 44, 2026
- LFM2.5-24B-A2B
Liquid AI · Efficient Agentic MoE · Week 43, 2026
More from Xiaomi
- MiMo-V2.6-Pro / Flash
Xiaomi · Open-Weight MoE Models · Week 40, 2026
- MiDashengLM-Gen
Xiaomi · Audio Processing · Week 33, 2026
- MiMo V2.5 ASR
Xiaomi · Speech-to-Text · Week 18, 2026
- MiMo-V2.5-Pro
Xiaomi · Code Generation · Week 17, 2026
- MiMo-V2-Omni
Xiaomi · Reasoning · Week 12, 2026
- MiMo V2 Flash
Xiaomi · Text-to-Video · Week 51, 2025
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.