# Arctic-Extract Technical Report

Source: [Arctic-Extract Technical Report](<https://www.sota2.com/research/paper/691ff200d6b0dd334292e611>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-22T05:02:37.875Z

Authors: Mateusz Chili\\'nski, Julita O{\\l}tusek, Wojciech Ja\\'skowski

Published: 2025-11-20T15:40:55.000Z

## Abstract

Arctic-Extract is a state-of-the-art model designed for extracting structural data (question answering, entities and tables) from scanned or digital-born business documents. Despite its SoTA capabilities, the model is deployable on resource-constrained hardware, weighting only 6.6 GiB, making it suitable for deployment on devices with limited resources, such as A10 GPUs with 24 GB of memory. Arctic-Extract can process up to 125 A4 pages on those GPUs, making suitable for long document processing. This paper highlights Arctic-Extract's training protocols and evaluation results, demonstrating its strong performance in document understanding.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.16470>)

[PDF](<https://arxiv.org/pdf/2511.16470.pdf>)
