Visual Web Navigation on WebGym OOD 2026 (test)
52.4Peak Success Rate (Easy)
AsyncWebRL (full)
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.06 | 52.4 | 34.3 | 7.1 | 45.4 | |
2026.06 | 51.8 | 35.1 | 11.3 | 44.4 | |
2026.06 | 50.9 | 24.1 | 4.8 | 42.9 | |
2026.06 | 47.3 | 30 | 5.2 | 40.5 | |
2026.06 | 46.6 | 27.8 | 5.5 | 39.3 | |
2026.06 | 37.4 | 24.3 | 1.2 | 32 | |
2026.06 | 32.5 | 11.2 | 0 | 26.2 |