Task-Oriented Dialogue on MultiWOZ 2.1 (test)
99.62Inform Rate
DarwinTOD
Updated 4d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.01 | 99.62 | 94.18 | 20.33 | 117.23 | |
2026.01 | 99.4 | 96.5 | 22.19 | 120.14 | |
2026.01 | 98.92 | 91.85 | 20.18 | 115.57 | |
2026.01 | 98.73 | 91.42 | 19.96 | 115.04 | |
2026.01 | 97 | 87.4 | 17.12 | 109.32 | |
2026.01 | 96.73 | 89.92 | 20.54 | 113.87 | |
2026.01 | 95.7 | 81.8 | 16.5 | 105.25 | |
2026.01 | 95.3 | 86.2 | 20.01 | 110.76 | |
2026.01 | 93.2 | 84.9 | 19.6 | 108.7 | |
2026.01 | 87.09 | 79.08 | 19.17 | 102.26 | |
2026.01 | 85 | 70.5 | 15.23 | 92.98 |