MiMo-V2.6 paper details data and RL results for open model
Original titlePaper thread on MiMo-V2.6, the newest open model and the latest to stream their RL run :)
AISummary
The MiMo-V2.6 paper thread reports on the newest open model, which also streams its RL run, focusing on data and RL experimental results rather than architecture. The Pro model reportedly rose from 58.41 to 72.57 on DeepSWE after RL, with the top published DeepSWE score cited at 74.
Source: wh · x.comPublished · added here