ExtractBench scores whether document agents return complete grounded records
ExtractBench evaluates 370 enterprise documents spanning 4,869 pages, eight business domains, and 67 document types. It measures value accuracy, record completeness, page- and word-level grounding, and cost, exposing truncation on long repeated-record documents.
Why it matters: A system can extract several fields correctly while silently dropping most rows from a schedule, table, claim list, or transaction record.