Someone posted a project here about a month ago where they compare models in head-to-head matchups similar to llmarena

Hasn't been updated for Mistral but so far gemeni seems to top the leaderboard.

jeffbee 2 days ago | parent | next [-]

OCR developers from decades past must be slapping their foreheads now that it seems users will wait a whole minute per page and be happy.

	▲	delaminator 2 days ago \| parent \| next [-]
		What they are happy about is accurate OCR. Getting the wrong answer really quickly is not the best goal.
	▲	culi 2 days ago \| parent \| prev [-]
		You can also sort by latency. dots.ocr has the lowest at 3.8s/page. And although it doesn't fare very well against much larger slower models, it's still streets ahead of traditional OCR techniques

andai 2 days ago | parent | prev | next [-]

How can something have a very high ELO but a very low win rate?

	▲	BlackLotus89 2 days ago \| parent [-]
		You don't loose any elo if your opponent is much stronger than you. Remis could in theory play a part as well.

pplonski86 2 days ago | parent | prev [-]

very nice comparison! I'd like to see on what examples OCR engines fail