Web Navigation on WebShop Implicit Hidden Drift
100Success Rate (Source)
Llama3.3-70B + GLOVE
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.01 | 100 | 83.4 | 6.8 | |
2026.01 | 99.4 | 76.6 | - | |
2026.01 | 98.4 | 91.6 | 15 | |
2026.01 | 96.2 | 78.4 | - | |
2026.01 | 95.3 | 76.6 | - | |
2026.01 | 95.3 | 76.9 | - | |
2026.01 | 95 | 98.4 | 20 | |
2026.01 | 94.4 | 97.5 | 20.6 | |
2026.01 | 75 | 100 | - | |
2026.01 | 75 | 100 | - | |
2026.01 | 46.9 | 75 | 5.3 | |
2026.01 | 42.5 | 61.6 | 25.4 | |
2026.01 | 35.6 | 69.7 | - | |
2026.01 | 34.4 | 36.2 | - |