# PaddleOCR vs Rossum

**Leader by Vioscale score:** Rossum

| Attribute | PaddleOCR | Rossum |
|---|---|---|
| **Vioscale score** | 48.9 (16% (low)) | 56.3 (41% (low)) |
| activity.commits_last_30d | 2 | - |
| adoption.dependent_repos | 549 | - |
| adoption.github_stars | 88,309 | - |
| deployment.options | `{"cloud":true}` | `{"cloud":true}` |
| description.long | PaddleOCR is an open-source OCR library that uses advanced machine learning algorithms to recognize and extract text from images and PDF documents. It offers a free cloud API service with support for large-scale batch document processing. | An intelligent document automation platform using AI agents to read, extract, and validate transactional document data, then automatically route it through approvals, data matching, and integration with business systems while maintaining full audit trails and compliance. |
| features.capabilities | - | `{"open_source":true,"soc2_type_ii":true,"pricing_model":"pay_per_page_api","prebuilt_models":true,"architecture_model":"managed_cloud_api","rpa_erp_integration":true,"custom_model_training":false,"handwriting_recognition":true,"human_in_the_loop_review":true,"llm_vlm_based_extraction":true,"web_scraping_to_markdown_or_json":false,"mit_or_apache_permissive_oss_license":true,"pdf_and_multimodal_image_ocr_parsing":true,"zero_data_retention_privacy_guarantees":false,"javascript_rendering_for_spa_web_scraping":false,"fine_tuned_document_layout_analysis_models":true,"human_in_the_loop_hitl_confidence_review_queue":true}` |
| integrations.count | - | 7 |
| integrations.list | - | `[{"name":"SAP"},{"name":"Coupa"},{"name":"Oracle"},{"name":"Workday"},{"name":"QuickBooks"},{"name":"Email"},{"name":"API"},{"name":"SFTP"},{"name":"PEPPOL"},{"name":"Scanners"},{"name":"Shared Drives"},{"name":"ERP Systems"},{"name":"NetSuite"},{"name":"Microsoft Dynamics"}]` |
| language.primary | Python | - |
| license.spdx | Apache-2.0 | - |
| market.availability | - | `{"primaryMarkets":[],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` |
| platform.support | `{"web":true}` | `{"cli":true,"web":true}` |
| pricing | `{"type":"open_source","summary":"Free open-source with cloud API access (20,000 pages/day)","freeTier":true,"sourceUrl":"https://paddlepaddle.github.io/PaddleOCR/","retrievedAt":"2026-08-20T16:36:20.946Z"}` | `{"type":"quote","plans":[{"free":false,"name":"Starter","features":["Unlimited seats","Document ingestion through email, API, or manual upload","Rossum Aurora Document AI for automated extraction","Validation screen for exception handling and human in the loop","Document archive & search","API access"],"commitment":"annual","description":"For scale ups who need to automate data capture","contactSales":true},{"free":false,"name":"Business","features":["Custom business logic to extract data and create custom workflows","Master data matching to match extracted values with databases","Duplicate detection & handling across channels","Custom functions & webhooks","Document workflow reporting","Integration with tech stack (SAP, Coupa, Workday, Oracle, etc.)"],"commitment":"annual","description":"For businesses who want to automate their document workflows end to end","contactSales":true},{"free":false,"name":"Enterprise","features":["Enterprise SSO","Sandbox testing environment","Extended master data matching","Preferred cloud location","Signature onboarding & success plans","Custom branding","Multi-document transactions","Custom domain for email ingestion","Additional sandbox","3-year document archive & search"],"commitment":"annual","description":"For mature businesses with complex use cases and highest level of customization and security","contactSales":true}],"addOns":[{"name":"Integrations"},{"name":"Service plans"}],"summary":"Customized based on document volume and workflow complexity. 14-day free trial. Minimum 1-year contract.","sourceUrl":"https://rossum.ai/pricing-plans/","retrievedAt":"2026-08-21T12:46:16.360Z","freeTrialDays":14}` |
| pricing.free_tier | yes | yes |
| pricing.model | open_source | quote |
| pricing.price_level | free | unknown |
| pricing.transparent | - | no |
| release.cadence_days | 15 | - |
| release.history | `[{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.7.0","date":"2026-06-11T12:09:14Z","type":"stable","version":"v3.7.0"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.6.0","date":"2026-05-28T11:42:29Z","type":"stable","version":"v3.6.0"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.5.0","date":"2026-04-21T08:40:47Z","type":"stable","version":"v3.5.0"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.4.1","date":"2026-04-14T05:47:27Z","type":"stable","version":"v3.4.1"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.4.0","date":"2026-01-29T11:19:45Z","type":"stable","version":"v3.4.0"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.3.3","date":"2026-01-20T07:27:09Z","type":"stable","version":"v3.3.3"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.3.2","date":"2025-11-13T14:46:03Z","type":"stable","version":"v3.3.2"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.3.1","date":"2025-10-29T11:49:29Z","type":"stable","version":"v3.3.1"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.3.0","date":"2025-10-16T12:58:29Z","type":"stable","version":"v3.3.0"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.2.0","date":"2025-08-21T11:11:07Z","type":"stable","version":"v3.2.0"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.1.1","date":"2025-08-15T08:55:16Z","type":"stable","version":"v3.1.1"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.1.0","date":"2025-06-29T06:57:35Z","type":"stable","version":"v3.1.0"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.0.3","date":"2025-06-26T10:04:31Z","type":"stable","version":"v3.0.3"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.0.2","date":"2025-06-18T16:38:08Z","type":"stable","version":"v3.0.2"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.0.1","date":"2025-06-05T03:27:00Z","type":"stable","version":"v3.0.1"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v3.0.0","date":"2025-05-20T12:16:51Z","type":"stable","version":"v3.0.0"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v2.10.0","date":"2025-03-07T07:03:56Z","type":"stable","version":"v2.10.0"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v2.9.1","date":"2024-10-22T05:57:17Z","type":"stable","version":"v2.9.1"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v2.9.0","date":"2024-10-18T15:43:04Z","type":"stable","version":"v2.9.0"},{"url":"https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v2.8.1","date":"2024-07-17T10:48:47Z","type":"stable","version":"v2.8.1"}]` | - |
| security.gdpr | - | yes |
| security.hipaa | - | yes |
| security.iso27001 | - | yes |
| security.soc2 | - | yes |
| security.vulnerabilities | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=paddleocr&per_page=100","last_12m":0,"max_severity":null}` | - |

## Capabilities (Document AI)

| Capability | PaddleOCR | Rossum |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Prebuilt models | - | ✓ |
| Custom model training | - | ✗ |
| Table extraction | - | - |
| Handwriting recognition | - | ✓ |
| Id document parsing | - | - |
| Human in the loop review | - | ✓ |
| Confidence scoring | - | - |
| LLM vlm based extraction | - | ✓ |
| RPA ERP integration | - | ✓ |
| Open source | - | ✓ |

*Source: Vioscale. Generated 2026-09-01T17:24:12.674Z. "-" = undocumented, not absent.*