Dharma Field Extractor

active

Version History

Field Extractormajor

Dharma-AI released a 2-billion-parameter LoRA-adapted model built on DharmaOCR-LITE v1.1 that returns typed, schema-matched JSON from document images. According to Dharma-AI, it scored 0.834 on its 1,638-case benchmark, above Claude Opus 5 at 0.816 and GPT-5.6 Luna at 0.741.

Coverage

model release

Dharma-AI's 2B Field Extractor scores 0.834 on its own benchmark, above Claude Opus 5's 0.816

Dharma-AI released Dharma Field Extractor, a 2-billion-parameter model that turns a document image into typed JSON, either open-ended or matched to a supplied schema. According to Dharma-AI, it scored 0.834 on its 1,638-case benchmark, above every frontier configuration tested, and runs self-hosted on a single L40S.

3 min read