Understand this story
SoMark has open-sourced OXR, a 1.3B-parameter document parsing model. According to a report dated October 21, 2026, the model ranks first on three benchmarks: olmOCR-Bench, OmniDocBench, and DocParsingBench; on a single RTX PRO 6000, its throughput is 3.05 times that of GLM-OCR, making it the fastest open-source result in the speed comparison. The report also states that OXR introduces RSI during the post-training stage: a VLM evaluates its own outputs, rollout divergence flags uncertainty, and a separate clustering model attributes it, based on which the next round of targeted data is generated; Rohan Paul calls OXR the first model to use RSI in document parsing. There are currently no subsequent developments.
AI-generated from public reports
Latest development · Report
SoMark open-sources the 1.3B document parsing model OXR, ranking first on three benchmarksDevelopments
1 confirmed developments
- Source:Rohan Paul
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 21
Rohan Paul
SoMark open-sources the 1.3B document parsing model OXR, ranking first on three benchmarks
SoMark has open-sourced the 1.3B document parsing model OXR, which ranks first on olmOCR-Bench, OmniDocBench, and DocParsingBench, achieves 3.05x the throughput of GLM-OCR on a single RTX PRO 6000, and is the fastest open-source result in the speed comparison. OXR introduces RSI during post-training: a VLM evaluates its own outputs, rollout divergence flags uncertainty, and a separate clustering model attributes it, based on which the next round of targeted data is generated. Rohan Paul calls OXR the first model to use RSI in document parsing, with the GitHub link in the comments.