abuse, disinformation, hate prompts
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Jailbreak evaluation | abuse, disinformation, hate prompts | Not Unsafe Rate99.9 | 4 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Jailbreak evaluation | abuse, disinformation, hate prompts | Not Unsafe Rate99.9 | 4 |