hermes-ai.net

Read docs →
HermesHermes Agent Docs
News
Back to News
modelImageOpen Source

StarDoc-AI's TeleOCR Beats Gemini 3 Pro at Document Parsing With 1.2B Parameters

A 1.2B parameter open-source vision-language model that parses both digital PDFs and warped phone-camera document photos in one framework

StarDoc-AI's TeleOCR Beats Gemini 3 Pro at Document Parsing With 1.2B Parameters
Source
AlphaSignal
Published
Author
AlphaSignal Newsroom
Read
1 min read

A 1.2B parameter open-source vision-language model that parses both digital PDFs and warped phone-camera document photos in one framework

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report

Next reads

EfficientNet-B0 RA Hits 800K Downloads as Developers Chase Tiny 5M Models
AlphaSignal · model

EfficientNet-B0 RA Hits 800K Downloads as Developers Chase Tiny 5M Models

Ant Group's Ming-Image Tops Open-Weight UI Design Rankings Among 81 Models
Artificial Analysis · news

Ant Group's Ming-Image Tops Open-Weight UI Design Rankings Among 81 Models

RelateAnything Maps Object Relationships 7.8x Faster Than Rival Systems
AlphaSignal · repo

RelateAnything Maps Object Relationships 7.8x Faster Than Rival Systems