Are you uploading PDFs that already have a text layer?
I don't currently subscribe to Gemini but on A.I. Studio's free offering when I upload a non OCR PDF of around 20 pages the software environment's OCR feeds it to the model with greater accuracy than I've seen from any other source.
I'm sorry but I don't see what "knowledge cutoff" has to do with what we were talking about- which is using a LLM find PDFs and other sources for research.
I don't currently subscribe to Gemini but on A.I. Studio's free offering when I upload a non OCR PDF of around 20 pages the software environment's OCR feeds it to the model with greater accuracy than I've seen from any other source.