Could you evaluate with MinerU, GOT-OCR, olmoOCR, MarkItDown?

Open dantetemplar opened this issue 10 months ago • 3 comments

I've collected some notable pipelines at https://github.com/dantetemplar/pdf-extraction-agenda

Feb 28 '25 22:02 dantetemplar

Thanks for sharing - we'll try to integrate more tools as we have bandwidth - olmocr is integrated into our benchmarks, will add results to our README shortly

Mar 01 '25 00:03 VikParuchuri

hello, I have test olmOCR. But I do fell it perform not good and has more mistake than minerU. Do you have better tools that can make a good perform in pdf-OCR?

Mar 06 '25 12:03 moro0v0

Thanks for sharing - we'll try to integrate more tools as we have bandwidth - olmocr is integrated into our benchmarks, will add results to our README shortly

Looking forward to your benchmark results against OlmOCR. Theirs is awesome, but very slow even on my 4090 GPU. Thanks.

Mar 13 '25 19:03 KastanDay