ExtractBench
ExtractBench is Every system fills the same JSON Schema from the same document. Scored on every record of every repeated structure, on nulls instead of invented values, and on a source box for each answer.. It is ranked #1564 on the Dev Radar, in Testing & observability, first seen 15 days ago and shared in 3 posts (41.9k views).
What people said about ExtractBench on X
We benchmarked GPT-6 Astra on hard document parsing and extraction tasks. It is the best frontier model for one-shotting document extraction over short and medium-sized documents: 📊 97.2% over short documents, achieving a new SOTA on our benchmark 📊 90.6% over medium documents But a few caveats: * it's pricy! The…
— @jerryjliu0, 14 days ago · 176 likes · see the post
Unlike other players in the OCR space, we don't block our competitors from accessing our platform. We're also fully committed towards open, reproducible benchmarks for document parsing and extraction - on ParseBench and ExtractBench respectively. It's important to give the industry a sense of how the pareto frontier…
— @jerryjliu0, 15 days ago · 89 likes · see the post
Astra is one of the best models we've tested at parsing complex documents with tables, at 93.2% on ParseBench. So it seems well suited for ad-hoc analysis over table-heavy documents e.g. in finance. To be fair, it's also at 10c per page so not suitable for document-heavy OCR workloads. Fable 5.1 still performs a…
— @jerryjliu0, 8 days ago · 54 likes · see the post
Alternatives to ExtractBench
- lint — @shadcn delivering the goodies for us
- TesterArmy — available soon
- evlog — A modern TypeScript logger built for everything you ship — scripts, libraries, jobs, edge, requests. Simple logs, wide…
- Sentry — Debug any software issue, onboard your team, and integrate with your systems. You get 14 days free on our Business…
- Expo — It's good to ship and touch grass. It's more relaxing with Observe
- con-leche — con-leche, a CONsistent LEan CHEcker: an external Lean checker proven (in Lean) to be consistent, meaning it does not…
ExtractBench in numbers
- Rank on the Dev Radar: #1564 of 1578
- Shared in 3 posts by 1 account: @jerryjliu0
- 41.9k views on those posts
- First seen 15 days ago, last shared 8 days ago
- Pricing seen by Jev: not stated
- Market: Testing & observability
FAQ
What is ExtractBench?
Every system fills the same JSON Schema from the same document. Scored on every record of every repeated structure, on nulls instead of invented values, and on a source box for each answer. It was first shared on X 15 days ago and is ranked #1564 on the Dev Radar.
Is ExtractBench free?
Pricing is not stated on the page we read.
Who shared ExtractBench?
1 account on X, including @jerryjliu0, in 3 posts totalling 41.9k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 14.4k posts from 4.7k X accounts over the last 21 days, 1.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 21:10 UTC. Full method.