Same here. I run Qwen3.8 Flash Next on my local machine and combine it with Opus 5.5 for plan making. The Qwen model feels like it's around Opus 4.x level performance most of the time.
But once in a while it gets into long reasoning loops, which is annoying. It seems less with the Swift model but I haven't benchmarked the difference between that one and the original.
But once in a while it gets into long reasoning loops, which is annoying. It seems less with the Swift model but I haven't benchmarked the difference between that one and the original.