Response Generation on AdvBench
0.95Win Rate
Chain-of-Thought
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.06 | 0.95 | 0.04 | 0.01 | |
2025.06 | 0.95 | 0.03 | 0.02 | |
2025.06 | 0.92 | 0.06 | 0.02 |
Chain-of-Thought
| Method | Links | |||
|---|---|---|---|---|
2025.06 | 0.95 | 0.04 | 0.01 | |
2025.06 | 0.95 | 0.03 | 0.02 | |
2025.06 | 0.92 | 0.06 | 0.02 |