I'm running minimax m2.7 locally (pretty good!). Tried stepfun 3.5 flash (kind of weak) and mimo v2.5 flash (tended to loop real hard). Looking forward to testing stepfun 3.7. Looks pretty good benchmark-wise.
Everything looked meh so far, until entered the visual recognition and reasoning chapter. That was very impressive. Very cool to see more vendors pushing towards models understanding images instead of just performing OCR.
I just wish they put a little bit of energy on making their service usable for non-chinese users. At the moment, their website assumes I speak chinese and when I manually click on "en", the website dynamically translates parts into english, I experience this as half baked solution.