Xiaomi put a live RL post-training dashboard for MiMo-V2.6 on the public internet.

MiMo team head Luo Fuli linked a minute-by-minute dashboard showing accepted and judged sample counts, pass rate (around 0.66 on n≈8,100-8,500), remaining and partial samples, prewarm and step numbers, plus token consumption and training cost. The run started September 15 at 10:32 UTC, and Luo says the team spent six months on how far RL scales, expanding compute, training environments and reward evaluation at once. No other lab publishes live post-training telemetry. If you're calibrating RL run economics, this is a free reference against a real run.