Tool-use Policy Auditing on τ2-BENCH Retail (base)
59.6PASS^4
Baseline
Updated 26d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 59.6 | 85.7 | 57.9 | |
2026.06 | 36 | 85.7 | 32.7 | |
2026.06 | 17.5 | 85.7 | 13.1 |
Baseline
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 59.6 | 85.7 | 57.9 | |
2026.06 | 36 | 85.7 | 32.7 | |
2026.06 | 17.5 | 85.7 | 13.1 |