Xiaomi launches open-source MiMo-V2.6 Pro & Flash, tops AI index at 46 among open models

burny_tech · x · 2026-09-23

Xiaomi officially introduced MiMo-V2.6, a family of two omnimodal models (Pro & Flash) built through scaled reinforcement learning.

The retweeter adds a notable detail: Xiaomi handles RL reward hacking by red-teaming its own RL environments and iteratively fixing them — better than most approaches, though possibly vulnerable to explicit goal-directed attacks like OpenAI's hacking swarm.

Related event: Xiaomi Open-Sources MiMo-V2.6, Topping Open-Weights Leaderboard with Livestreamed RL Training(39 posts)→

Original post →

More from coding & agent

coding & agent channel →