Mathematical Reasoning on GSM8k (Usage/Attack Accuracy)
55.95Attack Accuracy
No-shield
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2024.10 | 55.95 | - | - | |
2024.10 | 55.07 | - | - | |
2024.10 | 54.91 | - | - | |
2024.10 | 54.55 | - | - | |
2024.10 | 53.83 | - | - | |
2024.10 | 53.67 | - | - | |
2024.10 | 53.07 | - | - | |
2024.10 | 51.31 | - | - | |
2024.10 | 49.75 | - | - | |
2024.10 | 47.79 | - | - | |
2024.10 | 40.94 | - | - | |
2024.10 | 40.5 | - | - | |
2024.10 | 37.07 | - | - | |
2024.10 | 35.18 | - | - | |
2024.10 | 32.67 | - | - | |
2024.10 | 21.53 | - | - | |
2024.10 | 20.92 | - | - | |
2024.10 | 16.81 | - | - | |
2024.10 | 14.96 | - | - | |
2024.10 | 12.5 | - | - | |
2024.10 | 10.81 | - | - | |
2024.10 | 6.22 | 0 | 33.11 | |
2024.10 | 6.09 | - | - | |
2024.10 | 5.61 | - | - | |
2024.10 | 4.58 | - | - | |
2024.10 | 4.56 | - | - | |
2024.10 | 4.15 | - | - | |
2024.10 | 4.05 | - | - | |
2024.10 | 3.91 | 0 | 30.1 | |
2024.10 | 2.84 | - | - | |
2024.10 | 2.41 | 0 | 15.51 | |
2024.10 | 2.36 | - | - | |
2024.10 | 1.74 | - | - | |
2024.10 | 1.43 | - | - | |
2024.10 | 1.34 | - | - | |
2024.10 | 1.29 | - | - | |
2024.10 | 1.04 | 0 | 37.13 | |
2024.10 | 0.93 | - | - | |
2024.10 | 0.43 | - | - | |
2024.10 | 0.23 | - | - |