We’re open-sourcing Pro and Flash, MiMo-V2.6-Distill-Qwen-9B, the technical report, 7K+ RL task environments, an end-to-end RL framework and composable mini-harnesses.
Reproduce, verify and build on the work.
Xiaomi MiMo open-sources Pro, Flash, and a 9B distilled model
AISummary
Xiaomi MiMo announced open-source releases of Pro and Flash, the MiMo-V2.6-Distill-Qwen-9B model, a technical report, over 7K RL task environments, an end-to-end RL framework, and composable mini-harnesses.
The attached table shows MiMo-V2.6-Distill-Qwen-9B after SFT and after RL compared with Qwen3.5-9B, with RL scores higher on most listed benchmarks, such as SWE-bench Verified at 66.2 versus 60.0.
AIWhy it matters
The table compares a 9B distilled model against Qwen3.5-9B on coding, cyber, and agent benchmarks, showing how the reinforcement learning stage changes results.
Post on XView on X
@XiaomiMiMo
A reply · the post it answers
Source: Xiaomi MiMo · x.comPublished · added here