Identity
- Type
- big tech
- Country label
- China
- HQ country
- China
- Founding country
- not in the notes
- Parent
- not in the notes
- Parent country
- not in the notes
- Country basis
- the research notes
Where this comes from
Convention D1: a dual label, HQ first, when the HQ, founding or parent country differ.
Models by Class
Models
ModelClassOpennessParametersReleased
FireRedVADaudio classification11 Feb 2026dots.ocrOCR and document30 Jul 2025FireRedASRspeech recognition2025Links
Organisationrednote (Xiaohongshu)big tech, China
rednote (Xiaohongshu)big tech, ChinaModelsFireRedVADrednote (Xiaohongshu), audio classificationdots.ocrrednote (Xiaohongshu), OCR and documentFireRedASRrednote (Xiaohongshu), speech recognition
FireRedVADrednote (Xiaohongshu), audio classificationdots.ocrrednote (Xiaohongshu), OCR and documentFireRedASRrednote (Xiaohongshu), speech recognitionUse Casesnone recorded
Who Runs Itnone recorded
Scores
| Benchmark | Model | Score | Who ran it | Setting |
|---|---|---|---|---|
| OmniDocBench | dots.ocr | 90.77 score | vendor-reported | overall |
| Real5-OmniDocBench | dots.ocr | 86.38 score | vendor-reported | overall |
Where this comes from
Every recorded score of this organisation's models, with who ran it. Scores from different settings are not directly comparable.
Sources
- arxiv.org/pdf/2606.03264 https://arxiv.org/pdf/2606.03264
- GitHub - studio-dots-ai/dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model github.com https://github.com/rednote-hilab/dots.ocr
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Rednote (Xiaohongshu)", https://aurion.semai.id/organisations/rednote/, records of October 2026.