Markdown edition

# Dharma describes document field extractor

> Dharma reports extraction results and costs.

By BIGCHANGE.AI Editorial

Published: 2026-11-05T13:11:38.592Z
Updated: 2026-11-05T13:11:38.592Z
Canonical: https://bigchange.ai/blog/dharma-document-field-extractor

![Conceptual illustration of a blank form and index cards on a desk.](https://bigchange.ai/api/media/file/document-fields-concept.png)
AI-generated conceptual illustration by BIG CHANGE.

Dharma AI [described its field extractor](https://huggingface.co/blog/Dharma-AI/dharma-field-extractor) on November 4.

## The big change

- Schemas specify fields; open requests do not.
- Dharma reports higher benchmark scores.
- A [trial](https://ocr-portal.prd-us-east-2.dharma-ai.com/login) is linked; weights are unconfirmed.

## From a page to fields

Dharma says invoice schemas can request supplier, number, due date and total. Open requests identify fields instead. Both return JSON; missing requested fields should return null.

A schema is useful because a receiving application needs predictable names and types. The [JSON Schema project](https://json-schema.org/overview/what-is-jsonschema) explains that a validator can check whether data conforms to declared structural rules. Valid structure alone does not establish that an extracted value matches the page; users still need a way to assess accuracy.

## What was measured

Dharma tested 546 documents in three scenarios—open, existing fields and absent fields—making 1,638 cases. Its composite combines field matching, value similarity and valid JSON. It reports 0.834 against Claude Opus 5’s 0.816, with low or adaptive-low comparator effort; this is not independent verification.

Dharma reports costs 6–147 times lower: provider list prices applied to measured tokens versus self-hosted GPU time on one L40S at $2.24 per hour. Hardware, utilization and latency affect costs; this excludes broader deployment costs and is not a product price.

Dharma says a LoRA trained on extraction examples adapts its two-billion-parameter OCR-LITE v1.1 checkpoint. The [older OCR model](https://huggingface.co/Dharma-AI/Dharma-OCR-LITE) has listed weights; its [paper](https://arxiv.org/abs/2604.14314) does not test Field Extractor. BIG CHANGE did not test it.

## Sources

- [Dharma report](https://huggingface.co/blog/Dharma-AI/dharma-field-extractor) — Benchmark.
- [JSON Schema: overview](https://json-schema.org/overview/what-is-jsonschema) — General structure and validation.
- [DharmaOCR research](https://arxiv.org/abs/2604.14314) — Earlier OCR models and benchmark.
- [DharmaOCR-LITE model card](https://huggingface.co/Dharma-AI/Dharma-OCR-LITE) — Earlier model and listed files.