Web Navigation on Mind2Web Cross-Domain (EA, AF1, StepSR, TaskSR)
53.25Element Accuracy (EA)
Upper Bound
Updated 20d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.03 | 53.25 | 60.27 | 48.89 | - | |
2026.03 | 52.89 | 58.96 | 48.54 | - | |
2026.03 | 52.81 | 59.98 | 48.42 | - | |
2026.03 | 52.65 | 58.78 | 48.13 | - | |
2026.03 | 52.55 | 58.3 | 48.28 | - | |
2026.03 | 52.44 | 58.47 | 48.16 | - | |
2026.03 | 51.97 | 59.33 | 47.75 | - | |
2026.03 | 47.6 | 57.86 | 43.99 | - | |
2026.03 | 47.34 | 57.21 | 43.71 | - | |
2026.03 | 47.2 | 58.07 | 43.66 | - | |
2026.03 | 46.7 | 57.09 | 43.32 | - | |
2026.03 | 46.66 | 57.88 | 43.26 | - | |
2026.03 | 46.62 | 57.25 | 43.04 | - | |
2026.03 | 45.28 | 57 | 41.68 | - | |
2025.09 | 42.8 | 45.2 | 38.1 | 1.7 | |
2026.03 | 42.3 | 48.8 | 37.1 | 1.9 | |
2026.03 | 40.9 | 46.3 | 35.5 | 1.7 | |
2025.09 | 40.6 | 41.3 | 36.6 | 1.6 | |
2025.09 | 38.5 | 39.8 | 35.6 | 1.5 | |
2025.09 | 37.9 | 37.7 | 35 | 1.4 | |
2025.09 | 37.3 | 38.1 | 34.4 | 1.2 | |
2026.03 | 36.4 | 41.6 | 32.6 | 0.7 | |
2025.09 | 36.3 | 38.5 | 32.4 | 1.1 | |
2025.09 | 35.8 | 37.9 | 31.9 | 1 | |
2025.09 | 33.3 | 36.5 | 30.1 | 0.7 | |
2026.03 | 21.6 | 52.8 | 26.4 | 2 |