@kushalbyatnal: Over 1 billion PDFs are created every day, but your agents still can’t read them reliably. Today we’re releasing Parse …

X AI KOLs Following Products
document-parsing pdf api ai-agents sota benchmark production

Summary

Extend released Parse 2.0, a state-of-the-art document parsing API that achieves top accuracy on real-world documents, outperforming competitors on the open-source RealDoc-Bench benchmark.

Over 1 billion PDFs are created every day, but your agents still can’t read them reliably. Today we’re releasing Parse 2.0, the most accurate document parsing API in the world. Extend already processes millions of pages daily for leading AI teams like Brex, Mercury, Opendoor, Flatiron Health, and hundreds of others. Now, its even better. Parse 2.0 is SOTA quality on RealDoc-Bench, our open source benchmark that measures agent success rate on real world docs that agents actually encounter in production. We trained Parse 2.0 on 1M+ pages of the hardest documents seen in production. Here’s how it stacks up: - #1 in healthcare, real estate, logistics, and financial services - 95.7% agent Q&A accuracy on 581 docs (next best: 92%) - 0.847 F1 on layout (next best: 0.759) Give it a try today and build production-ready document agents with Extend.
Original Article
View Cached Full Text

Cached at: 05/26/26, 06:56 PM

Over 1 billion PDFs are created every day, but your agents still can’t read them reliably.

Today we’re releasing Parse 2.0, the most accurate document parsing API in the world.

Extend already processes millions of pages daily for leading AI teams like Brex, Mercury, Opendoor, Flatiron Health, and hundreds of others. Now, its even better.

Parse 2.0 is SOTA quality on RealDoc-Bench, our open source benchmark that measures agent success rate on real world docs that agents actually encounter in production.

We trained Parse 2.0 on 1M+ pages of the hardest documents seen in production. Here’s how it stacks up:

  • #1 in healthcare, real estate, logistics, and financial services
  • 95.7% agent Q&A accuracy on 581 docs (next best: 92%)
  • 0.847 F1 on layout (next best: 0.759)

Give it a try today and build production-ready document agents with Extend.

too close to home

it’s a layout aware parser! so yes, it preserves table schema

works great! check out this example from our blog post

try it out!

yup works really well on handwriting! check out this example:

layout contains a lot of critical info for agents!

yup, can be deployed fully on prem!

5k pages parsed, and then PAYG from there!

brb booking more flights

that was the goal!

I had to triple check the stat

thanks!

thank you!

fine tuned models!

ah, that should work if you enable this config option!

thanks! the many many hours of painstaking annotation was worth it

we love working with the mercury team!!

as always

thanks!

btw, at least 1x/week I find myself missing the June UI/UX

thanks!

thanks Mo!

thank you!

thanks ishaan!

thanks! Starcloud is amazing btw

thanks reyab!

amazing stuff @kushalbyatnal !

appreciate it bryce!

thanks tommy!

thanks!

thanks zeno!

appreciate it!

Similar Articles