MiMo-V2.5
An iterative release in the open-source MiMo reasoning model series developed by Xiaomi's technical team. It demonstrates strong performance on code and mathematical reasoning tasks and employs reinforcement learning for post-training optimization.
Timeline (last 90 days)
Naive-N0.5-Flash was publicly trained based on Xiaomi's MiMo-V2.5 model
Xiaomi's MiMo series is an open-source reasoning model released by Xiaomi; MiMo-V2.5 demonstrates strong performance on code and mathematical reasoning tasks and employs reinforcement learning for post-training optimization
MiMo-V2.6 and V2.5 belong to the same architectural category, and previously deployed server-side components can be used directly, including hybrid sliding window attention + global attention, the MiMo reasoning and tool-call parser, and DFlash speculative decoding.
All Facts (3)
Naive-N0.5-Flash was publicly trained based on Xiaomi's MiMo-V2.5 model
50%UnverifiedXiaomi's MiMo series is an open-source reasoning model released by Xiaomi; MiMo-V2.5 demonstrates strong performance on code and mathematical reasoning tasks and employs reinforcement learning for post-training optimization
50%UnverifiedMiMo-V2.6 and V2.5 belong to the same architectural category, and previously deployed server-side components can be used directly, including hybrid sliding window attention + global attention, the MiMo reasoning and tool-call parser, and DFlash speculative decoding.
50%