DeceptionBench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Deception Detection | DeceptionBench (full 600-sample) | Response AUROC97.4 | 15 | |
| Deception Detection | DeceptionBench | Response AUROC93.5 | 6 | |
| Instruction Signal Recovery | DeceptionBench | Judge Score (R)68.6 | 4 |
Showing 3 of 3 rows