GUI Navigation on Multimodal-Mind2Web Cross-Task
71.5Step Success Rate
HTML-T5-XL
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.03 | 71.5 | 76.4 | 78.8 | |
2025.03 | 66.4 | - | - | |
2025.03 | 62.3 | - | - | |
2025.02 | 55.7 | 60.8 | 88.9 | |
2025.03 | 54.7 | 60.5 | 89.7 | |
2025.02 | 53.2 | 56.5 | 90.3 | |
2025.03 | 52.7 | - | - | |
2025.03 | 52.7 | 59.2 | 88.9 | |
2025.02 | 50.7 | 53.4 | 88.1 | |
2025.02 | 48.3 | 51.8 | 88 | |
2025.03 | 44.9 | 51.7 | 87.2 | |
2025.02 | 44.8 | 48.1 | 88 | |
2025.03 | 40.2 | 46.4 | 73.4 | |
2025.02 | 40.2 | 46.4 | 73.4 | |
2025.02 | 39.6 | 43.6 | 86.6 | |
2025.03 | 39.4 | 42.4 | 87.6 | |
2025.02 | 35.6 | 38 | 52.9 | |
2025.02 | 33.2 | 36.5 | 82.9 | |
2025.02 | 32.3 | 40.8 | 63.1 | |
2025.02 | 30 | - | - | |
2025.03 | 29.2 | 33.7 | 72.5 | |
2025.03 | 25.5 | 28.3 | 87 | |
2025.02 | 23.7 | 26.3 | 86.2 | |
2025.03 | 20.8 | 23.8 | 86.8 | |
2025.02 | 20.8 | 23.8 | 86.8 | |
2025.02 | 16.8 | 19.4 | 59.2 | |
2025.03 | 15.6 | 19.1 | 86.1 |