Web Content Extraction on WCEB 1.0 (simple)
83.63ROUGE-N F1Dripper_fallback
Evaluation Results
| Method | Links | |
|---|---|---|
| Dripper_fallbackmode=Html+TEXT2025.11 | 83.63 | |
| Drippermode=Html+TEXT2025.11 | 82.93 | |
| Trafilaturamode=TEXT2025.11 | 81.22 | |
| Trafilaturamode=Html+TEXT2025.11 | 78.96 | |
| magic-htmlmode=Html+TEXT2025.11 | 77.8 | |
| Readabilitymode=Html+TEXT2025.11 | 77.44 | |
| justTextmode=TEXT2025.11 | 74.45 | |
| Goose3mode=TEXT2025.11 | 74.32 | |
| html2textmode=TEXT2025.11 | 72.73 | |
| news-pleasemode=TEXT2025.11 | 70.51 | |
| BoilerPy3mode=Html+TEXT2025.11 | 65.32 | |
| BoilerPy3mode=TEXT2025.11 | 64.81 | |
| GNEmode=Html+TEXT2025.11 | 51.38 | |
| ReaderLM-v2mode=TEXT2025.11 | 37.18 |