MinerU
Evidence review 4.3/5Open-source PDF document parsing and data extraction tool
Which tools fit your actual task?
Describe the task and required capabilities, then compare catalog candidates by budget and language. Verify task performance separately.
At a glance
MinerU is an open-source AI tool focused on parsing PDF document content and extracting structured data, supporting the recognition and conversion of complex elements such as tables, formulas, and images. It is based on deep learning models and can convert PDF files into editable formats such as Markdown and JSON, suitable for scenarios including academic papers, technical documents, and contracts. As a product that can be deployed directly for use, MinerU provides two usage methods: command line and Python API, making it suitable for users who need to process PDF documents in batches.
Best-in-class for open-source batch PDF-to-structured-data work, if you accept self-hosting costs.
Catalog information score 72/100 is not measured task performance. The separate evidence review scored 4.3/5.
Verification & Changelog
Verification and change timeline
Only public append-only events appear here; automated and human verification are labelled separately.
- Review sources checked
Automated review published · MinerU
An automated review checked 自定义深度学习模型 against public sources and structured scenarios.
Source evidence checked - Review sources checked
Automated review published · MinerU
An automated review checked 自定义深度学习模型 against public sources and structured scenarios.
Source evidence checked - Imported historical snapshot
Historical import snapshot · MinerU
Migrated from an existing public catalog; does not indicate that discovery, verification, or testing occurred at this time.
Historical import; this does not mean newly discovered, updated, or tested.
Imported record
Review findings
This is a source review, not a measured task run. The recorded product/version does not identify an executed model. Manual publication alone does not establish hands-on testing; inspect benchmark runs for actual models, tasks and dates.
Based on public information: MinerU is an open-source PDF parsing tool from OpenDataLab that converts complex PDF/Office documents into LLM-ready Markdown/JSON. Task completion 4.5: the official description covers tables, formulas and images, with both a CLI and a Python API for batch pipelines. Output quality 4.0: the structured Markdown/JSON fits RAG and agent workflows, but no accuracy benchmark for hard layouts is published, so precision needs independent verification. Speed 3.5: parsing relies on a custom deep-learning model deployed locally, so throughput depends on GPU and batch size rather than instant cloud responses. Chinese optimisation 4.5: maintained by a China-based team, with Chinese academic papers and technical docs as its headline scenarios. Value 5.0: open source, self-hostable, no per-page fees, low marginal cost at batch scale. Strengths are open source, private deployment and structured multi-format output; the gaps are self-deployment effort and the absence of an official online demo or speed baseline.
Best-in-class for open-source batch PDF-to-structured-data work, if you accept self-hosting costs.
- Score
- 4.3/5
- Product/version recorded in source
- 自定义深度学习模型
- Updated
- Nov 1, 2026
- Reviewer
- OKCodex 每日自动评测系统(公开来源与结构化场景)
- Process
- Automated evidence review
Best for
Developers and teams parsing papers or technical docs at scale to build RAG pipelines
Less suitable for
Light users who want plug-and-play online parsing without deploying or tuning models
This review uses public sources and structured scenarios. It does not claim hands-on human testing.
Product details
- Model
- 自定义深度学习模型
- Category
- Data · Productivity
- Autonomy
- L2
- Pricing
- Free
- Languages
- Chinese / English
- Product/version recorded in source
- Checked
Common questions
What pricing information is recorded for MinerU?
The catalog lists a free plan. Confirm current prices, included features and usage limits with the provider; this catalog does not verify a total cost or budget ceiling.
What do the catalog and review scores mean for MinerU?
The catalog information score is 72/100; it is not measured task performance. The separate source-supported review records 4.3/5 for the product/version recorded in its source: 自定义深度学习模型. This is a source review, not a measured task run. The recorded product/version does not identify an executed model. Manual publication alone does not establish hands-on testing; inspect benchmark runs for actual models, tasks and dates. It is automated source analysis, not a claim of hands-on human testing. The two score scales are not interchangeable.
What product information is available for MinerU?
Open-source PDF document parsing and data extraction tool
What does the published review conclude about MinerU?
Best-in-class for open-source batch PDF-to-structured-data work, if you accept self-hosting costs.
Share evidence details
Weekly OKCodex briefing
Every Wednesday: demand signals, agent reviews, and editorial perspective.
No spam · Unsubscribe anytime
Related agents
Related by catalog categories, models, or text similarity. This does not verify task performance or budget fit.