Finland’s education system is failing. Should we look to Asia?

Sorry, but this is incredibly naive.

Is your comment hand-waving optimism, or do you have evidence that 1) deep learning classifiers are better than teachers at evaluating student competency across a wide range of fields, and 2) that using those tests (vs, say, teacher-observed in-class participation) results in better alignment to the educational needs of the student?

As https://curmudgucation.blogspot.com/2022/01/the-search-for-c... points out, "no computer algorithm can, for instance, understand whether or not your supporting evidence provides good, er even accurate, support" for the thesis, which seems right to me.

For example, https://www.wbur.org/hereandnow/2020/09/03/online-learning-a... has the story of student who answered the question "How did the location of Constantinople help it grow wealthy and prosperous?" with "It was between the Aegean and the Black seas, which made it a hub for boats of traders and passengers. It was also right between Europe and Asia Minor, which made it a huge hub for trade, and it was on many trade routes of the time. Profit Diversity Spain Gaul China India Africa" - and got a perfect score from the robograder.

I'll switch to something that is more measurable - physical education.

Why isn't physical education included in the PISA score?

We can measure someone's speed, weight, height, jump distance, weight lifting ability, and a lot more.

Do those give a good metric by which to judge someone's physical education grade? Or do we also need to include teamwork, improvement, and sportsmanship?

We need somebody to yell at when things go wrong.