Have you ever scanned a paper document and saved it as a PDF, only to find yourself frustrated because you "cannot copy the ...
Baidu open-sources Unlimited OCR 2, an MIT-licensed 3B OCR model scoring 77.1 on MarathonDocBench for hundred-page document parsing.
Datalab’s OmniParseBench is an open OCR benchmark scoring parsers with 16,288 pass/fail tests across 2,937 pages, 92 languages.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results