Agent Trajectory Verification Agreement on WebTailBench
7.7Unterminated Rate
Native Verifier
Updated 9d ago
Evaluation Results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.04 | 7.7 | 62.5 | 63.5 | 39.9 | 23 | 37 | 72 | 78 | 40 | 17 | 49 | 64 | 65 | 31 | |
2026.04 | 17 | 39.6 | 39.6 | 23.2 | 30 | 20 | 76 | 70 | 50 | 14 | 25 | 77 | 64 | 49 |