Xiaomi livestreams MiMo-v2.6 RL training run, hits ~60% of deepswe in one day

zainhas · x · 2026-09-17

Xiaomi is publicly livestreaming the full reinforcement learning run for its MiMo-v2.6 and 2.6 flash models. Per the poster, the run started just one day ago and has already reached roughly 60% progress on the deepswe benchmark — an unusually transparent move for a major model training effort.

Related event: Xiaomi live-streams MiMo-V2.6 RL training with public dashboard(5 posts)→

Original post →

More from Models

Models channel →