630-scenario real-world benchmark
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Safety Guardrail Classification | 630-scenario real-world benchmark (independent set) | Verdict Accuracy95.4 | 5 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Safety Guardrail Classification | 630-scenario real-world benchmark (independent set) | Verdict Accuracy95.4 | 5 |