It also puts a thumb on the scale for AI, which tends to emit pages of text to answer simple questions.

Sounds like any post-secondary, graduate student, or management consultant out there being there are, very often, page/word count or hours requirements. Considering the model corpora, wordiness wins out.

The chart is actually words "thought or written" so I guess they are running up the numbers even more by counting Claudes entire inner monologue, on top of what it ultimately outputs.