WHAT NEW IN X11.01 SUN

AI collections from X · 22 collections · 63,170 posts

gemini-4POST

Own OCR benchmark: Gemini 4 Argon trails Gemini 3.0 Flash

Testing tricky PDF-to-Markdown conversion, a user finds Gemini 4 Argon worse at OCR than Gemini 3.0 Flash, saying it prefers to fabricate content rather than extract messy text as-is.

Johannes Schmidt
@spaceMonsterArchived 5 days agoOriginally posted 2026.10.26
Johannes Schmidt @spaceMonsterOriginally posted 2026.10.26
Open original on X

@theo Gemini 4 Argon is worse than Gemini 3.0 Flash in OCR tasks in my own benchmark (i should publish that soon). I have a parkour of tricky PDFs and it's task is to convert them to markdown Gemini 4 is more comfortable to lie about content than to extract the messy content as is

x.com/spacemonster/status/2114484817937027439Archived 2026.10.26 10:01