Agent Safety on AuraGen
95.31Accuracy
Extractor
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.02 | 95.31 | 94.06 | 98.96 | 89.62 | |
2026.02 | 94.01 | 92.13 | - | 88.79 | |
| 93.88 | 92.23 | - | 91.13 | ||
2026.02 | 93.62 | 91.55 | - | 88.59 | |
2026.02 | 93.36 | 91.79 | 94.06 | 89.62 | |
2026.02 | 92.96 | 91.79 | 94.06 | 88.53 | |
2026.02 | 92.06 | 89.69 | - | 89.27 | |
2026.02 | 90.62 | 88.35 | 91 | 85.85 | |
2026.02 | 90.49 | 87.29 | - | 83.06 | |
2026.02 | 86.91 | 83.81 | - | 81.07 | |
2026.02 | 85.55 | 80 | 93.67 | 69.81 | |
2026.02 | 84.77 | 78.92 | 92.41 | 68.87 | |
2026.02 | 80.08 | 71.82 | 86.67 | 61.32 | |
2026.02 | 79.39 | 64.96 | - | 56.99 | |
2026.02 | 79.03 | 56.32 | - | 50.38 | |
2026.02 | 78.12 | 66.27 | 91.67 | 51.89 | |
2026.02 | 70.7 | 63.05 | 65.98 | 60.38 | |
2026.02 | 70.42 | 68.42 | - | 67.25 | |
2026.02 | 69.84 | 40.79 | - | 29.25 | |
| 69.17 | 71.76 | - | 66.2 | ||
2026.02 | 64.38 | 17.14 | - | 13.77 | |
2026.02 | 63.28 | 26.56 | 77.27 | 16.04 | |
2026.02 | 63.21 | 30.36 | 58.62 | 20.48 | |
2026.02 | 62.74 | 8.14 | 87.5 | 4.27 | |
2026.02 | 62.2 | 16.84 | - | 10.54 | |
2026.02 | 62.11 | 19.83 | - | 11.32 | |
2026.02 | 61.91 | 20.63 | 65 | 12.26 | |
2026.02 | 61.72 | 18.33 | 78.57 | 10.38 | |
2026.02 | 61.56 | 0 | 0 | 0 | |
2026.02 | 60.94 | 27.54 | 59.38 | 17.92 | |
| 60.56 | 53.87 | - | 45.45 | ||
2026.02 | 60.53 | 15.44 | - | 12.83 | |
2026.02 | 60.47 | 10.51 | - | 13.43 | |
2026.02 | 60.16 | 10.53 | - | 5.66 | |
2026.02 | 60.14 | 19.91 | 51.22 | 12.35 | |
| 59.77 | 52.97 | - | 41.6 | ||
| 59.7 | 53.39 | - | 58.96 | ||
2026.02 | 58.59 | 0 | 0 | 0 | |
2026.02 | 58.59 | 25.01 | 18.36 | 13.87 | |
2026.02 | 58.59 | 7.02 | 50 | 3.77 | |
2026.02 | 58.25 | 13.66 | 70 | 7.57 | |
2026.02 | 58.2 | 0 | 0 | 0 | |
2026.02 | 58.01 | 55.79 | - | 44.26 | |
2026.02 | 57.81 | 1.82 | 25 | 0.94 | |
2026.02 | 57.81 | 3.57 | 33.33 | 1.89 | |
2026.02 | 57.42 | 18.05 | 44.44 | 11.32 | |
2026.02 | 53.92 | 51.76 | - | 39.22 |