What it measures

Multi-source document parsing benchmark covering PDF textbooks, academic papers, financial reports, newspapers, handwritten notes, and complex formulas/tables.

Reading the measurement

Study what information the model receives and which inference the answer requires. A question may mix recall, visual perception, deduction and search. Use task breakdowns to find the mechanism behind a headline gain.

Published evaluation

Overall parsing score; OmniDocBench · end-to-end evaluation. The table retains the source’s reported model and evaluation configuration.

Where this fits in an evaluation suite

Ask what the task actually requires: recall, deduction, search, or a mixture. Separate closed-book reasoning from retrieval and tool-assisted problem solving.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

Overall parsing score; OmniDocBench · end-to-end evaluation. The table retains the source’s reported model and evaluation configuration.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.

PRIMARY EVIDENCE & FURTHER READING

  1. OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations — published result table ↗

    Linke Ouyang, Yuan Qu, Hongbin Zhou, Jiawei Zhu, Rui Zhang, Qunshu Lin et al. · 2024

    All 20 authors

    Linke Ouyang, Yuan Qu, Hongbin Zhou, Jiawei Zhu, Rui Zhang, Qunshu Lin, Bin Wang, Zhiyuan Zhao, Man Jiang, Xiaomeng Zhao, Jin Shi, Fan Wu, Pei Chu, Minghao Liu, Zhenxiang Li, Chao Xu, Bo Zhang, Botian Shi, Zhongying Tu, Conghui He

Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.