Boo Bench
Boo Bench is Leaderboard + paper. It is ranked #71 on the AI Radar, in RAG & memory, first seen 53 days ago and shared in 15 posts (191.8k views).
What Boo Bench says about itself
We built a haunted house to scare parsers into repeating themselves.
Boo Bench Boo Bench a ParseBench feature set Boo Bench is a haunted house of 179 pages built to scare document parsers into repeating themselves. Boo Bench is built to capture the pages that scare VLMs (cause them to make mistakes) but most specialized document OCR APIs perform well on. It is a playful and simple litmus test for understanding the need for specialized models, tools, and agent harnesses for document processing, beyond simply straight-shotting documents to VLMs. A Boo is an element on a page that scares a parser. We frequently see failure modes where certain pages cause parsers to go into repetition loops or stop parsing…
What people said about Boo Bench on X
Introducing the Document Parsing Protocol (DPP) There are hundreds of different OCR models and tools, but they might all parse a document in different ways. Some errors are very clear-cut (e.g. hallucinating text, or completely misaligning a table), but many errors are much more ambiguous (e.g. how to represent split…
— @jerryjliu0, 8 days ago · 792 likes · see the post
OCRia-1 is the best document parsing model for complex tables in PDFs: nested headers, merged cells, no cell borders, and extreme density within a single page. It tops multiple parsing benchmarks on table accuracy. 91.5% on ParseBench, 92.9% on olmOCR-bench, 84.1% on PulseBench-Tab, 83.2% on fr-bench-pdf2md. We…
— @jerryjliu0, 10 days ago · 295 likes · see the post
We've built the most accurate document extraction system on the planet. Extract Max Effort will spend dynamic tokens reasoning about every visual detail across hundreds of pages to ensure that you get the maximum accuracy possible. Check out this massive well log report below. It's more accurate and still cheaper…
— @jerryjliu0, 4 days ago · 252 likes · see the post
Alternatives to Boo Bench
- auto-ontology — Auto Ontology 🔥
- arXiv.org — Contextual embeddings represent chunks of a document with respect to the document's global context. These models are…
- liteparse — A fast, helpful, and open-source document parser. Contribute to run-llama/liteparse development by creating an account…
- ModelBest — ModelBest — On-Device Open-Source Model Platform
- OpenDocRouter — Set the model to llamaindex/ocria-1 in your parse request to try it. New accounts start with $5 in credit
- claude-mem — Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses…
Boo Bench in numbers
- Rank on the AI Radar: #71 of 10402
- Shared in 15 posts by 5 accounts: @jerryjliu0, @llama_index
- 191.8k views on those posts
- First seen 53 days ago, last shared 1 days ago
- Pricing seen by AGK Intelligence: free
- Market: RAG & memory
FAQ
What is Boo Bench?
Leaderboard + paper It was first shared on X 53 days ago and is ranked #71 on the AI Radar.
Is Boo Bench free?
Yes, it is free to use.
Who shared Boo Bench?
5 accounts on X, including @jerryjliu0, @llama_index, in 15 posts totalling 191.8k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.