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

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 Media

Source: LlamaIndex (X) | 2026-08-17