OpenAI
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text-based safety moderation | OpenAI | F1 Score82.3 | 26 | |
| Question Answering | OpenAI (in-domain) | Accuracy0.8956 | 12 | |
| Diverse Nearest Neighbor Search | OpenAI dataset | Search Cost0.331 | 4 |
Showing 3 of 3 rows