MPDocBench
A benchmark for multi-page document parsing, typically covering documents on the order of tens of pages. It emphasizes layout understanding and content extraction, including complex structures such as tables, charts, and multi-column layouts.
Timeline (last 90 days)
Unlimited OCR 2 achieves state-of-the-art results on the MPDocBench benchmark.
Baidu says Unlimited OCR 2 achieves SOTA performance on the tens-of-pages-level benchmark MPDocBench and the hundreds-of-pages-level benchmark MarathonDocBench.
MPDocBench focuses on layout understanding and content extraction for multi-page documents (typically on the order of tens of pages), covering complex structures such as tables, charts, and multi-column layouts.
All Facts (3)
Unlimited OCR 2 achieves state-of-the-art results on the MPDocBench benchmark.
50%UnverifiedBaidu says Unlimited OCR 2 achieves SOTA performance on the tens-of-pages-level benchmark MPDocBench and the hundreds-of-pages-level benchmark MarathonDocBench.
50%UnverifiedMPDocBench focuses on layout understanding and content extraction for multi-page documents (typically on the order of tens of pages), covering complex structures such as tables, charts, and multi-column layouts.
50%