HS
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Narrative Understanding | HS | First-Token Accuracy87.8 | 24 | |
| Commonsense Reasoning | HS | Accuracy85.87 | 23 | |
| Human Safety / Alignment | HS | HS Average1.84 | 18 | |
| Code Generation | HS (test) | BLEU67.1 | 10 | |
| Query representation clustering | HS (test) | ARI0.0723 | 3 |
Showing 5 of 5 rows