Your anecdote seems to clash heavily with the results of the benchmark announced in the article. I suppose that is part of the jagged experience of agentic AI
The benchmark announced in the article seems to be around weird edge cases (which are often important) and whether it can prompt the person with relevant information rather than just listening to what they want to do.
Top tier tax professionals can do pretty well on this benchmark (better than agents) but won't hit 100%.
The kind of people spending time preparing oodles of returns would not do very well on this metric, though (especially midway through that pile of returns, as opposed to "think carefully about this trick question").
The OP said it was a complicated return so anyone assuming OPs anecdote is in line with the article is filling the lines in themselves with a lot of assumptions