Agent Trajectory Verification Agreement on Mind2Web OM2W
5Unterminated Rate
Native Verifier
Updated 9d ago
Evaluation Results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.04 | 5 | 32.2 | 25.8 | 15.8 | 26 | 18 | 80 | 66 | 0.52 | 17 | 23 | 78 | 55 | 0.42 | |
2026.04 | 7.2 | 62 | 64.9 | 48.6 | 27 | 42 | 67 | 74 | 0.3 | 24 | 49 | 63 | 67 | 0.27 |