My comment referred to the typical Markov chain type word prediction, which is the mechanism behind the 'sentence context' you referred to in those custom IMEs.

What I described is basically taking that mechanism and baking it into the standard OS without all the custom personalization options the IMEs offer and just offer a ready to use "English + OtherLang" option.

I don't think iOS does anything like that, but there you can still reduce the threshold at which you'll auto-correct and get a significant improvement.

Just goes to show that on all platforms there are still plenty of trade-offs to be explored.