Agentic Tool-use on tau2-bench Airline
63.5Pass@1
CODEDELEGATOR
Updated 4d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.01 | 63.5 | 53.7 | 48.5 | 46 | - | |
2026.01 | 62 | 50.7 | 44.5 | 42 | - | |
2026.01 | 59 | 45.3 | 37 | 32 | - | |
2026.01 | 58.5 | 47 | 40.5 | 36 | - | |
2026.01 | 57 | 49.3 | 45 | 42 | - | |
2026.01 | 56.5 | 47.3 | 41.5 | 40 | - | |
2026.01 | - | - | - | - | 42.6 | |
2026.01 | - | - | - | - | 16 | |
| - | - | - | - | 50 | ||
2026.01 | - | - | - | - | 62.6 |