@llama_index: Most document extraction APIs can't tell you where a value came from. For ExtractBench, we scored grounding strictly: a…

X AI KOLs Timeline Tools

Summary

ExtractBench is a new benchmark for document extraction that strictly scores grounding accuracy, showing VLMs and coding agents lack evidence while LlamaExtract Agentic Plus leads with high page-level and word-level performance.

Most document extraction APIs can't tell you where a value came from. For ExtractBench, we scored grounding strictly: a field only counts if the value AND its citation are correct, word-level box at IoU 0.5. A perfect box around a wrong value earns nothing. Results: VLMs and coding agents return no evidence at all — zero at both levels. Among systems that do return boxes, the best word-level F1 is still under 50%. And grounding collapses with length: one specialized API goes from 61.7% page-level on short docs to 0.0% on long ones. LlamaExtract Agentic Plus leads at both levels — 84.9% page-level, 46.4% word-level — and holds at 87.1% on long documents where others hit zero. Every extracted value should come with receipts. ExtractBench now gives the field a baseline to track it Blog: https://lnkd.in/gNm97fXp Paper: https://lnkd.in/euAfScWx
Original Article
View Cached Full Text

Cached at: 08/17/26, 04:14 PM

Most document extraction APIs can’t tell you where a value came from.

For ExtractBench, we scored grounding strictly: a field only counts if the value AND its citation are correct, word-level box at IoU 0.5. A perfect box around a wrong value earns nothing.

Results: VLMs and coding agents return no evidence at all — zero at both levels. Among systems that do return boxes, the best word-level F1 is still under 50%. And grounding collapses with length: one specialized API goes from 61.7% page-level on short docs to 0.0% on long ones.

LlamaExtract Agentic Plus leads at both levels — 84.9% page-level, 46.4% word-level — and holds at 87.1% on long documents where others hit zero.

Every extracted value should come with receipts. ExtractBench now gives the field a baseline to track it

Blog: https://lnkd.in/gNm97fXp Paper: https://lnkd.in/euAfScWx


LinkedIn

Source: https://lnkd.in/gNm97fXp LinkedIn## This link will take you to a page that’s not on LinkedIn

Because this is an external link, we’re unable to verify it for safety.

https://www.llamaindex.ai/blog/introducing-extractbenchThis experience is optimized for Chrome, Edge, and Safari

Similar Articles

ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction

Hugging Face Daily Papers

ExtractBench is a new benchmark for schema-guided enterprise document extraction, evaluating value accuracy, record completeness, grounding, and cost across 4,869 pages of enterprise documents. The authors find that commercial VLMs struggle with long documents while coding agents are more accurate but costly, and LlamaExtract AgenticPlus leads on all metrics.