Tencent releases 5B omni-modal parsing model Youtu-Parsing-Omni
Tencent Youtu Lab published Youtu-Parsing-Omni on Hugging Face, a compact 5B omni-modal parsing model that turns a document page, natural image, chart or flowchart, geometry figure, audio clip or audio-visual video into a single structured JSON output, with the output family selected by a task prompt. The model card says a single omni encoder handles image, audio and interleaved audio-visual video inputs, and that a vLLM plugin, pinned serving settings, task prompts and inference examples are included. Tencent reports 96.96 Overall on OmniDocBench v1.6, 75.08 Avg. on OmniParsingBench as the best open-weight model behind Gemini-3-Pro, and competitive results against specialized models on chemical-structure and music-score recognition; all of these benchmarks are vendor-reported and were not independently verified in the supplied material.
If the self-reported results hold, a 5B model can match specialized parsers on document benchmarks while covering documents, images, audio and video through one schema, giving teams an open-weight option for self-hosted structured extraction.
tencent/Youtu-Parsing-Omni Image-Text-to-Text • 5B • Updated 1 day ago • 3.05k • 122
license: other license_name: youtu-parsing license_link: https://huggingface.co/tencent/Youtu-Parsing-Omni/blob/main/LICENSE library_name: transformers pipeline_tag: image-text-to-text tags:
- document-parsing
- ocr
- omni
- multimodal
- audio
- video
- custom_code
#Tencent#Tencent Youtu Lab#Youtu-Parsing-Omni#Hugging Face#vLLM#OmniDocBench#OmniParsingBench#Gemini-3-Pro#ChemOCR#PDMX-Synth