{"slug": "xiaomi-open-sources-mimo-v2-6-models-after-scaling-reinforcement-learning", "title": "Xiaomi open-sources MiMo-V2.6 models after scaling reinforcement learning", "summary": "Xiaomi released and open-sourced the MiMo-V2.6 series, including the native multimodal MiMo-V2.6-Pro and MiMo-V2.6-Flash models, plus MiMo-V2.6-Distill-Qwen-9B and reinforcement-learning research resources. Xiaomi said MiMo-V2.6-Pro scored 46 on the Artificial Analysis Intelligence Index, ahead of Kimi K3 at 44 and GLM-5.3 at 45, making it the highest-ranked open-weight model on the index, while leading closed-source models scored 53. The two models completed 30 reinforcement-learning steps in less than six days using about 750,000 trajectories, at reported costs of $2.62 million for Pro and $850,000 for Flash, and the release adds 3D spatial reasoning, multimodal perception, computer-use capabilities and a desktop client.", "body_md": "Xiaomi has released and open-sourced the MiMo-V2.6 series, including the native multimodal MiMo-V2.6-Pro and MiMo-V2.6-Flash models. Xiaomi also released MiMo-V2.6-Distill-Qwen-9B and research resources for reinforcement learning.\n\nMiMo-V2.6-Pro scored 46 on the Artificial Analysis Intelligence Index, ahead of Kimi K3 at 44 and GLM-5.3 at 45, according to Xiaomi’s cited comparison. The company described it as the highest-ranked open-weight model on the index, while noting that leading closed-source models scored 53.\n\nThe two models completed 30 reinforcement-learning steps in less than six days, using about 750,000 trajectories at reported costs of $2.62 million for Pro and $850,000 for Flash. The release also adds 3D spatial reasoning, multimodal perception, computer-use capabilities and a desktop client. [[Xiaomi MiMo](https://mimo.mi.com/docs/zh-CN/news/latest/v2-6), in Chinese]", "url": "https://wpnews.pro/news/xiaomi-open-sources-mimo-v2-6-models-after-scaling-reinforcement-learning", "canonical_source": "https://technode.com/2026/09/22/xiaomi-open-sources-mimo-v2-6-models-after-scaling-reinforcement-learning/", "published_at": "2026-09-22 07:06:38+00:00", "updated_at": "2026-09-22 07:24:48.196462+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "ai-products", "machine-learning"], "entities": ["Xiaomi", "MiMo-V2.6", "MiMo-V2.6-Pro", "MiMo-V2.6-Flash", "MiMo-V2.6-Distill-Qwen-9B", "Artificial Analysis Intelligence Index", "Kimi K3", "GLM-5.3"], "alternates": {"html": "https://wpnews.pro/news/xiaomi-open-sources-mimo-v2-6-models-after-scaling-reinforcement-learning", "markdown": "https://wpnews.pro/news/xiaomi-open-sources-mimo-v2-6-models-after-scaling-reinforcement-learning.md", "text": "https://wpnews.pro/news/xiaomi-open-sources-mimo-v2-6-models-after-scaling-reinforcement-learning.txt", "jsonld": "https://wpnews.pro/news/xiaomi-open-sources-mimo-v2-6-models-after-scaling-reinforcement-learning.jsonld"}}