Web Agent Navigation on BookingArena 1.0 (test)
66.7Booking.com Success Rate
UI-TARS
Updated 1mo ago
Evaluation Results
| Method | Links | ||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.02 | 66.7 | 83.3 | 0 | 26.9 | 33.3 | 66.3 | 50 | 68.9 | 0 | 25 | 16.7 | 28.9 | 33.3 | 76.8 | 0 | 56.8 | 33.3 | 57.2 | 0 | 37.9 | 33.3 | 48.6 | 33.3 | 61.9 | 0 | 11.7 | 33.3 | 56.2 | 66.7 | 80 | 33.3 | 80 | 50 | 84.4 | 33.3 | 59.2 | 16.7 | 26.7 | 0 | 35 | 26.7 | 53.6 | |
| 50 | 89.2 | 66.7 | 88.4 | 50 | 85.9 | 50 | 85.6 | 50 | 81.9 | 80 | 80 | 50 | 73.8 | 33.3 | 72.9 | 16.7 | 68 | 33.3 | 66.2 | 33.3 | 63.9 | 33.3 | 59.8 | 16.7 | 56.7 | 20 | 50.2 | 16.7 | 48.3 | 0 | 41.1 | 0 | 33.3 | 0 | 31.2 | 0 | 12.2 | 0 | 12.2 | 29.9 | 60.2 | ||
2026.02 | 20 | 44 | 0 | 40.3 | 33.3 | 66.5 | 0 | 50 | 40 | 71.7 | 16.7 | 53.1 | 16.7 | 40.5 | 0 | 9.7 | 50 | 80 | 33.3 | 43.3 | 50 | 76.4 | 33.3 | 40 | 0 | 10 | 16.7 | 47.4 | 16.7 | 62.2 | 16.7 | 38.9 | 16.7 | 36.1 | 0 | 27.5 | 20 | 36 | 0 | 34.4 | 18.8 | 45.3 | |
2026.02 | 0 | 6.7 | 33.3 | 62 | 0 | 50.5 | 0 | 56.7 | 33.3 | 58.3 | 33.3 | 49.6 | 16.7 | 59.5 | 0 | 34.1 | 0 | 43 | 33.3 | 56.3 | 16.7 | 38.9 | 33.3 | 60.7 | 16.7 | 30 | 16.7 | 36.9 | 16.7 | 59.2 | 16.7 | 78.9 | 50 | 76.7 | 16.7 | 60.5 | 0 | 17.8 | 0 | 36.1 | 16.8 | 48.7 | |
2026.02 | 0 | 55.6 | 16.7 | 68.5 | 50 | 84.2 | 20 | 77.7 | 50 | 75 | 83.3 | 98.3 | 50 | 66.7 | 20 | 66 | 25 | 80.4 | 50 | 69 | 20 | 58.3 | 40 | 67 | 25 | 56.7 | 16.7 | 49 | 25 | 65 | 50 | 90.8 | 80 | 96 | 40 | 88.1 | 0 | 47.7 | 0 | 23.9 | 33 | 68.7 |