Skip to content

Liquid image-to-JSON extraction VLM judge score

A display-only Liquid AI extraction metric measuring judged agreement between extracted values and the source image.

1 models

Higher is better.

  1. 1LFM2.5-VL-1.6B-ExtractLiquid AI90.6
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
VLM-judged extraction accuracy
Tasks
Image-to-JSON extraction
Authors
Liquid AI (2026)

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.