WoW
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Question Answering | WoW | Average Performance Score84.3 | 20 | |
| Knowledge-grounded Dialogue | WoW | F1 Score17.35 | 15 | |
| Retrieval-Augmented Generation | WoW | LLM Score88.87 | 11 | |
| Dialogue | WoW | F1 Score14.77 | 8 | |
| Automatic Speech Recognition | WoW Out-of-domain (test) | WER12.7 | 6 | |
| Knowledge-grounded Dialog Generation | WoW (Seen) | Appropriateness Score4.5 | 6 | |
| Natural Language Generation | WoW | Mean Relevance4.68 | 5 | |
| Enterprise Workflow Automation | WoW | Perfect Match30.5 | 4 | |
| Knowledge-grounded Dialogue | WoW (test) | Dialogue Turns163 | 2 |
Showing 9 of 9 rows