There's a lot of real-world documents that are scanned, rotated, handwritten, or some combination of...

Jerry Liu on X: "There's a lot of real-world documents that are scanned, rotated, handwritten, or some combination of any of these elements. This week we created a comprehensive document extraction benchmark that contains documents tagged with various "perception challenges", along with other" / X

Jerry Liu

@jerryjliu0

There's a lot of real-world documents that are scanned, rotated, handwritten, or some combination of any of these elements. This week we created a comprehensive document extraction benchmark that contains documents tagged with various "perception challenges", along with other tags denoting task challenges, table structure, business domain. These docs include regulatory filings, hand-filled tax forms, photocopied docs, sensor noise, and more. Codex is surprisingly good at scans, but not great on rotated docs. OCR solutions are reasonable on rotations/handwriting but struggle on more general scans. Check out ExtractBench! ArXiv:

arxiv.org/pdf/2607.29677

Site:

extractbench.ai

LlamaIndex 🦙

@llama_index

Aug 13

Every document extraction system has a perception blind spot. We mapped them. For ExtractBench, we tested 14 systems on documents that weren't born digital: 1950s regulatory filings, hand-filled tax forms, and pages degraded with fax thresholding, photocopier tone curves, sensor

Show more

$

00:00

/$

11:28 PM · Aug 14, 2026

3.9K

Views

5

3

24

21