SoMark's open-source OXR model tops three document parsing charts
The story so far
No overview yet — start with the coverage timeline below.
Developments
2 developments
- 30 Oct, 08:00 · 1 reportsYoutu-Parsing-Omni has been releasedHugging Face Daily Papers:Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities
- 27 Oct, 15:41 · 2 reportsOXR Open SourceQbitAI:The domestically developed open-source OXR tops three document parsing benchmarks with 1.3B parameters.
Coverage timeline
Follow the coverage to see every side of the story.
- QbitAIFeaturedThe domestically developed open-source OXR tops three document parsing benchmarks with 1.3B parameters.
The SoMark team has open-sourced the 1.3B document parsing model OXR, ranking first on three benchmarks: OmniDocBench (97.18), olmOCR-Bench (87.84), and DocParsingBench (87.76).
- Hugging Face Daily PapersYoutu-Parsing-Omni: One Encoder, One Schema, All Modalities
Youtu-Parsing-Omni encodes documents, images, audio, and video into spatiotemporal structured records, achieving optimal parsing performance through self-evolution strategies and distillation. Single-modal encoders share weights and integrate cross-modal information, a single architecture unifies outputs for ten parsing tasks. The 5B parameter version achieved top scores of 96.96 and 75.08 on OmniDocBench v1.6 and OmniParsingBench, with code and weights open-sourced.
- QbitAIOXR open-source model tops three charts, achieving high precision and speed with 1.3B parameters
The OXR open-source model topped all three benchmark tests, OmniDocBench, olmOCR-Bench, and DocParsingBench, with complete parsing speed exceeding PaddleOCR-VL-1.6 and MinerU2.5-Pro