| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| bAbI dialog 1.0 (OOV) | QRN | Avg Error Rate0.023 | 22 | 4d ago | |
| WoW (Wizard of Wikipedia) (test) | INFO-RAG | F1 Score11.38 | 8 | 4d ago | |
| DSTC2 | QRN | Average Error Rate0.489 | 7 | 4d ago | |
| bAbI dialog | QRN+ | Average Error Rate1.5 | 7 | 4d ago | |
| DSTC2 (test) | QRN | Average Error Rate48.9 | 7 | 4d ago | |
| bAbI dialog Standard 1.0 | QRN | Average Error Rate1.5 | 7 | 4d ago | |
| Real-world Dialog Domains Aggregate | DFPO | Average Accuracy87.31 | 6 | 4d ago | |
| Financial Services Out-of-Domain | DFPO | Accuracy84.3 | 6 | 4d ago | |
| Social & Entertainment Out-of-Domain | Accuracy87.13 | 6 | 4d ago | ||
| Healthcare & Wellness Out-of-Domain | Accuracy90.23 | 6 | 4d ago | ||
| Transportation & Travel Out-of-Domain | DFPO | Accuracy90.5 | 6 | 4d ago | |
| Life Services In-Domain | Accuracy86.73 | 6 | 4d ago |