Web Agent Tasks on Mind2Web Cross-Domain
55.7Ele.Acc
Magma-8B
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.02 | 55.7 | 80.6 | 47.3 | |
2024.11 | 45.5 | 85.7 | 42 | |
2025.02 | 45.5 | 85.7 | 42 | |
2026.06 | 44.9 | 46 | 39.7 | |
2025.02 | 42.4 | 69.3 | 36.8 | |
2024.01 | 42.1 | 66.5 | 39.6 | |
2024.11 | 42.1 | 66.5 | 39.6 | |
2026.06 | 40.9 | 36.3 | 35.5 | |
2026.06 | 40.6 | 41.3 | 36.6 | |
2025.02 | 40.4 | - | 34.9 | |
2024.11 | 39.4 | 86.8 | 35.2 | |
2024.11 | 38.9 | 85.3 | 34.1 | |
2024.01 | 37.1 | 46.5 | 26.4 | |
2024.11 | 37.1 | 46.5 | 26.4 | |
2025.02 | 37.1 | 46.5 | 26.4 | |
2024.11 | 36.3 | 81.8 | 30.7 | |
2026.06 | 35.8 | 37.9 | 31.9 | |
2025.02 | 33.1 | - | 28.5 | |
2024.11 | 24.4 | 83.9 | 21.4 | |
2025.12 | 23.9 | - | 19.1 | |
2024.01 | 23.2 | 84.8 | 20.8 | |
2024.11 | 23.2 | 84.8 | 20.8 | |
2025.02 | 23.2 | 84.8 | 20.8 | |
2024.01 | 21.6 | 52.8 | 18.6 | |
2025.02 | 20.7 | 64.3 | 18 | |
2024.11 | 20.6 | 42 | 15.5 | |
2025.12 | 19.3 | - | 14.5 | |
2025.02 | 17.9 | 74.5 | 17.6 | |
2025.12 | 15.5 | - | 11.6 | |
2024.01 | 14.2 | 44.7 | 11.9 | |
2025.02 | 14.2 | 83.1 | 11.7 | |
2024.01 | 14.1 | 84.3 | 12 | |
2024.11 | 14.1 | 84.3 | 12 | |
2025.02 | 14.1 | 84.3 | 12 | |
2025.12 | 12.8 | - | 9.7 | |
2025.12 | 10.8 | - | 7.5 | |
2025.12 | 9.5 | - | 7.2 | |
2025.12 | 8.8 | - | 6.1 | |
2025.02 | 6.5 | 81.4 | 5.2 | |
2025.02 | 3.6 | 83 | 3 | |
2025.12 | 2.1 | - | 1.1 | |
2025.02 | - | 23.7 | - |