Multi-turn tool calling on τ2-bench
38Airline Score
DiGiT-TC
Updated 1mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.01 | 38 | 17.62 | 6.1 | 8.77 | - | |
2026.04 | 38 | - | 35.1 | 3.5 | 25.5 | |
2026.01 | 30 | 17.02 | 6.14 | 14.91 | - | |
2026.04 | 30 | - | 36.8 | 12.3 | 26.4 | |
2026.04 | 28 | - | 36.8 | 10.5 | 25.1 | |
2026.04 | 26 | - | 45.6 | 17.5 | 29.7 | |
2026.01 | 24 | 13.56 | 7.02 | 9.65 | - | |
2026.04 | 24 | - | 43 | 15.8 | 27.6 | |
2026.04 | 22 | - | 16.7 | 14 | 17.6 | |
2026.04 | 22 | - | 4.4 | 9.7 | 12 | |
2026.01 | 20 | 17.77 | 22.8 | 10.5 | - | |
2026.01 | 14 | 16.08 | 17.54 | 16.7 | - | |
| 0.48 | - | 0.614 | 0.482 | 0.525 | ||
| 0.473 | - | 0.605 | 0.453 | 0.51 | ||
| 0.467 | - | 0.658 | 0.488 | 0.538 | ||
| 0.427 | - | 0.611 | 0.38 | 0.473 | ||
2026.04 | 0.42 | - | 0.629 | 0.412 | 0.487 | |
| 0.407 | - | 0.626 | 0.64 | 0.558 | ||
| 0.407 | - | 0.585 | 0.596 | 0.529 |