Joe

DL/ML generalist | Founding AI engineer @ Extend

[Joe @BajorJoseph]

Feels great to finally share this one with the world!

Long array extraction can get really tough, and this simulates the most difficult situations we've encountered in production.

I'll make a blog post soon talking about the generator setup, lots of findings there as well!

[Kushal Byatnal @kushalbyatnal]

we created a new, open source eval (LongArray-Extract) for one of the hardest problems in document processing: how to extract every row out of long documents

some highlights:
- Extend's array extraction is SOTA (99.2%)
- 3x faster than the next closest competitor (5 min vs 14 min)

it's based on examples we've seen in production:
> bank statements with 2,000+ transactions
> clinical adverse-event listings with 1,000+ events
> legal filings with hundreds of numbered factual paragraphs

if you've ever built a document pipeline on hundred page docs with thousands of listings, you know exactly how quickly things break

we open sourced the benchmark + dataset so teams can inspect the docs, run the harness, and compare results directly

[Joe @BajorJoseph]

I’m really proud of where this benchmark ended up! I’ve been working in the NLP space for a while and this is the easily the best benchmark I have worked on, we worked really hard to make it the most comprehensive one out there.

[Kushal Byatnal @kushalbyatnal]

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.

[Joe @BajorJoseph]

@kushalbyatnal Finally some good benchmarks in the space!

[Joe @BajorJoseph]

@ApplyWiseAi @ExtendHQ All containerized on cloud infra. We're not making any embeddings in this case, its custom model stack + llm calls