I wouldn't discount what Apple has done... they've created and integrated some really good niche stuff in their CPUs to do more than typical ARM designs. The graphics cores are pretty good in their own right even. Not to mention the OS/Software integration including accelerated x86 and unified memory usage in practice.

AMD has done a LOT for parallelization and their server options are impressive... I mean, you're still talking 500W+ in total load, but that's across 128+ cores. Strix Halo scaling goes down impressively to the ~10-15W range under common usage, not as low as Apple does under similar loads but impressive in its own way.