Xiaomi opens up its RL training run, V2.6-Pro trails GPT-6 Astra
Xiaomi published its full RL training process along with environments and code; V2.6-Pro scores 46 on Artificial Analysis, behind GPT-6 Astra's 53, but costs about 45 times less per task.
Xiaomi makes this 1500hp EV supercar that holds test track records in Germany, and has just shipped a credible frontier model after a public RL training demo. Claude says: Xiaomi is the first major lab to run its production RL in the open. It streamed the run live and disclosed the key numbers: about 750,000 trajectories, 30 steps in under six days, roughly $2.62M for Pro and $0.85M for Flash. It says it's releasing the training environments and RL code so others can reproduce the results. CodeMidas shows that filtered, verified tasks beat larger unfiltered sets. Open-sourcing such environments lowers the barrier for every open lab and pressures closed labs whose advantage partly rests on proprietary RL data. https://arxiv.org/html/2609.22068v1 V2.6-Pro is the top open-weights model and ties Grok 4.7 at 46 on Artificial Analysis. It still trails Claude Opus 5 (51) and GPT-6 Astra (53), with the widest gaps on hard long-horizon tests like Terminal-Bench 4.0 (34.9 vs 49.0 and 59.6). Its edge is cost: it's roughly 45× cheaper per task than Opus 5.