Public KG record
OmniParseBench
Recorded overview
KG-recorded benchmark related to OmniParseBench; detailed English notes are not yet available.
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: 16,288 项测试、2,937 页、2,343 份文档、22 个测试套件
- Capabilities: 按标签切片查看解析器测试得分
- Integrations: 可通过 uv 安装；提供 CLI 与 Python 评分接口
- Languages: 覆盖 92 种语言
- Languages: Dataset spans 92 languages
- Limitations: 不支持布局的结果不计入总分
- Supported types: 输入为 PDF 页面或页面图像
- Requirements: Python 3.11+
Evidence coverage
The KG currently records 11 known information dimensions and has 6 undocumented dimensions, linked to 1 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- olmOCR-bench — related to
- Claude Sonnet 5.5 — evaluated on
- Gemini 3.8 Flash — evaluated on
- olmOCR-bench — related to
- pass/fail unit tests — uses