Web Agent Tasks on Mind2Web Cross-Task
59Element Accuracy
MINDACT
Updated 4d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2024.02 | 59 | 80.6 | 53.2 | 26 | |
2024.02 | 58.1 | 80.5 | 51.7 | 26.6 | |
2024.02 | 58 | 79.7 | 51.3 | 26.4 | |
2024.02 | 57.5 | 82 | 50 | 23.2 | |
2024.02 | 56.2 | 82.5 | 47.1 | 24.7 | |
2024.01 | 55.1 | 75.7 | 52 | - | |
2024.11 | 55.1 | 75.7 | 52 | - | |
2025.02 | 54.8 | 79.7 | 43.4 | - | |
2024.02 | 54.5 | 79.5 | 47.8 | 19.8 | |
2024.02 | 51 | 80.8 | 42.6 | 18.4 | |
2024.02 | 49.6 | 79.9 | 41.9 | 18.4 | |
2024.02 | 47.8 | 78.8 | 41.4 | 16.1 | |
2025.02 | 46.4 | 73.4 | 40.2 | - | |
2025.02 | 43.4 | - | 38.2 | - | |
2024.02 | 43.2 | 79.1 | 36.6 | 14.2 | |
2024.11 | 42.4 | 87.6 | 39.4 | - | |
2025.02 | 42.4 | 87.6 | 39.4 | - | |
2024.01 | 41.6 | 60.6 | 36.2 | - | |
2024.11 | 41.6 | 60.6 | 36.3 | - | |
2025.02 | 41.6 | 60.6 | 36.2 | - | |
2024.11 | 39.9 | 88.6 | 37.2 | - | |
2024.11 | 39.7 | 88 | 36.9 | - | |
2024.11 | 37.7 | 86.4 | 33.2 | - | |
2024.02 | 36.8 | - | - | - | |
2025.12 | 30.8 | - | 26.1 | - | |
2025.02 | 30.2 | - | 26.9 | - | |
2024.01 | 28.3 | 87 | 25.5 | - | |
2024.11 | 28.3 | 87 | 25.5 | - | |
2025.02 | 28.3 | 87 | 25.5 | - | |
2025.12 | 24 | - | 19.6 | - | |
2025.02 | 23.8 | 86.8 | 20.8 | - | |
2024.11 | 22.4 | 53 | 17.6 | - | |
2025.02 | 21.5 | 67.7 | 19.6 | - | |
2024.11 | 21.4 | 85.2 | 18.6 | - | |
2025.12 | 21 | - | 16.8 | - | |
2025.12 | 20.6 | - | 17.3 | - | |
2024.01 | 20.3 | 56.6 | 17.4 | - | |
2024.01 | 20.2 | 52 | 17.5 | - | |
2025.02 | 19.1 | 86.1 | 15.6 | - | |
2024.01 | 15.9 | 86.7 | 13.3 | - | |
2024.11 | 15.9 | 86.7 | 13.3 | - | |
2025.02 | 15.9 | 86.7 | 13.3 | - | |
2025.12 | 15.8 | - | 12.3 | - | |
2025.12 | 14.7 | - | 11.6 | - | |
2025.12 | 13.5 | - | 11.4 | - | |
2025.02 | 11 | 85.6 | 8.5 | - | |
2025.02 | 8.3 | 83.9 | 6.6 | - | |
2025.12 | 5.8 | - | 4.1 | - | |
2024.02 | 4.3 | 27.6 | 1.9 | 1 | |
2025.02 | - | 20.3 | - | - |