Baidu Open-Sources Wenxin Unlimited OCR 2: Claims Arbitrary Page Count Parsing, Self-Reported SOTA on Long-Document Benchmarks
Baidu released and open-sourced Wenxin Unlimited OCR 2, introducing a sparse reference sliding window attention mechanism to parse thousands of pages in one request, with self-reported SOTA scores.
On October 27, Baidu released and open-sourced Wenxin Unlimited OCR 2, an optical character recognition model optimized for ultra-long document parsing. Baidu claims it is the first globally to achieve "arbitrary page count" document parsing, pushing the processing limit from dozens of pages to infinity.
According to Baidu, this breakthrough is enabled by a newly proposed Sparse Reference Sliding Window Attention (SR-SWA) mechanism. Inspired by human reading habits, it uses page gating to narrow visual reference ranges and combines with unlimited-horizon decoding to significantly reduce computational and memory overhead for long documents. Tests show the model can parse over 3,600 pages of the entire Harry Potter series in a single request.
In public benchmark tests, Baidu self-reported that Wenxin Unlimited OCR 2 achieved composite scores of 84.6 on MPDocBench and 77.1 on MarathonDocBench, claiming end-to-end SOTA performance and leading models like Qwen 3.8-Max and Gemini-3.8-Flash. The code and model weights are now open-sourced on GitHub and Hugging Face under the MIT license.