PDF Parsing on Internal PDF Parsing Dataset
99Text Extraction AccuracyProposed
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Proposed2026.04 | 99 | 93 | 96 | 98 | 100 | 100 | 100 | 100 | 100 | |
| PyMuPDF2026.04 | 98 | 75 | 76 | 95 | — | 82 | 79 | 91 | — | |
| Tika2026.04 | 98 | — | — | 82 | — | 69 | — | 69 | — | |
| PDFPlumber2026.04 | 97 | — | 81 | — | — | 88 | 88 | — | — | |
| unstructured2026.04 | 97 | — | 82 | 86 | — | 73 | 85 | 72 | — | |
| PDFMiner2026.04 | 97 | — | — | 96 | — | 91 | — | 91 | — |