Main HTML Extraction on MainWebBench
83.99ROUGE-N F1 (All)Dripper_fallback
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Dripper_fallbackmode=Html+MD2025.11 | 83.99 | 90.1 | 83.92 | 77.99 | 79.64 | 86.73 | 90.67 | 80.28 | |
| Drippermode=Html+MD2025.11 | 81.82 | 88.37 | 81.78 | 75.36 | 76.93 | 83.68 | 88.89 | 76.71 | |
| magic-htmlmode=Html+MD2025.11 | 70.91 | 78.11 | 70.95 | 63.67 | 66.81 | 84.71 | 84.7 | 46.78 | |
| Readabilitymode=Html+MD2025.11 | 64.91 | 73.7 | 65.25 | 55.7 | 58.96 | 77.74 | 78 | 46.08 | |
| Trafilaturamode=Html+MD2025.11 | 63.58 | 72.77 | 63.91 | 53.96 | 55.05 | 60.06 | 73.27 | 57.5 | |
| Trafilaturamode=MD2025.11 | 62.37 | 71.15 | 62.79 | 53.05 | 54 | 57.41 | 71.68 | 57.66 | |
| Trafilaturamode=TEXT2025.11 | 60.49 | 69 | 60.88 | 51.49 | 52.71 | 55.66 | 69.55 | 56.81 | |
| html2textmode=MD2025.11 | 59.77 | 74.99 | 58.12 | 46.78 | 59.37 | 77.29 | 71.29 | 54.94 | |
| BoilerPy3mode=TEXT2025.11 | 54.13 | 63.47 | 54.48 | 44.34 | 43.8 | 48.33 | 65.9 | 46.95 | |
| GNEmode=Html+MD2025.11 | 51.48 | 64.77 | 49.42 | 40.98 | 41.29 | 54.95 | 61.6 | 32.96 | |
| news-pleasemode=TEXT2025.11 | 50.12 | 53.99 | 52.5 | 43.07 | 41.93 | 51.18 | 67.01 | 40.73 | |
| jusTextmode=TEXT2025.11 | 47.7 | 51.32 | 50.7 | 40.1 | 39.62 | 37.79 | 66.52 | 52.22 | |
| BoilerPy3mode=Html+MD2025.11 | 47.66 | 64.43 | 47.06 | 31.74 | 37.83 | 55.32 | 61.57 | 41.03 | |
| Goose3mode=TEXT2025.11 | 43.54 | 45.14 | 46.45 | 38.08 | 35.89 | 29 | 63.76 | 30.64 | |
| ReaderLM-v2mode=MD2025.11 | 22.64 | 33.74 | 20.78 | 14.03 | 18.01 | 24.31 | 29.27 | 15.37 |