OmniDocBench

Headlines · 2

1. 5d
   SoMark open-sources 1.3B OXR document-parsing model

   SoMark has open-sourced OXR, a roughly 1.3B-parameter document-parsing model that separates layout analysis from content recognition and reading-order prediction. It can process 13 types of document elements into Markdown or JSON, while its post-training pipeline uses recursive self-improvement to turn errors and uncertain samples from unlabeled documents into new training data. The team reported first-place scores on three benchmarks and a 101-second end-to-end parse time for 100 pages on one RTX PRO 6000, but these performance claims have not been independently verified.

   量子位（原生 RSS） · 🔥 3
2. Oct 9
   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.

   腾讯混元 · Hugging Face · 🔥 0

Experience and discussion from the community

Share my OmniDocBench experienceAsk about OmniDocBench