Just to add as we are discussing mainly ARM vs x86 now... that is just a small part of the whole device. Just look at the SD OLED vs LCD. They managed to have OLED screen that is significantly better than the LCD one while using less power on AVG which is a huge deal to battery life and it either allows you to compensate with more power to SOC to achieve better performance at the same battery life or take the saving and go with higher battery life... and that's just screen.

Then they optimized the PCB layout, PCB components, etc.... to get both better cooling and efficiency.

I think that what is currently holding them back is both the SOC available and the actual efficiency of given parts combined. Getting improvement in both areas at once will lead to a significant change but one or the other alone will not tip the scales towards significant upgrade.

I dunno, I think you may be underestimating ARM here. I've heard that the overhead from translating the machine code is a lot lower than you might think, because so much X86 code is optimized down to a RISC-like subset of the instruction set already. And if that overhead isn't too daunting in the common cases, the more robust power management on the ARM side of the chip market might be able to make up the difference in a handheld environment for most users. Obviously it's a huge amount of work to nail the software, and it would be on top of the work they were already doing on Linux, so I'm not saying it'll definitely be in the next iteration, but I could definitely imagine it happening eventually.