We benchmarked 18 LLMs on OCR (7k+ calls) — cheaper/old models oftentimes win. Full dataset + framework open-sourced. [R]

TLDR; We were overpaying for OCR, so we compared flagship models with cheaper and older models. New mini-bench + leaderboard. Free tool to test your own documents. Open Source. We’ve been looking at OCR / document extraction workflows and kept seeing the same pattern: Too many teams are either stuck in legacy OCR pipelines, or are overpaying badly for LLM calls by defaulting to the newest/ biggest model. We put together a curated set of 42 standard documents and ran every model 10 times under