PERSUADE
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Judge Performance | PERSUADE | CCC0.955 | 32 | |
| Non-Agentic Performance Evaluation | Persuade (test) | Mean Score53.2 | 4 | |
| Safety Evaluation | Persuade | Cost per Accuracy Point ($)0.0008 | 4 |
Showing 3 of 3 rows