Toxicity Evaluation on AttaQ 1402 prompts (test)
0.042Max Toxicity Score
RAD
Updated 1mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.01 | 0.042 | 0.034 | 11.31 | 0.1 | - | |
2026.01 | 0.047 | 0.035 | 6.75 | 0.2 | - | |
2026.01 | 0.074 | 0.051 | 3.29 | 0.6 | - | |
2026.01 | 0.084 | 0.059 | 3.01 | 0.7 | - | |
2026.01 | 0.086 | 0.057 | 7.24 | 1.4 | - | |
2026.01 | 0.086 | 0.067 | 2.51 | 0 | 1.07 | |
2026.01 | 0.097 | 0.067 | 2.75 | 1.4 | - | |
2026.01 | 0.111 | 0.075 | 3.67 | 2.6 | - | |
2026.01 | 0.13 | 0.091 | 2.5 | 3.7 | - | |
2026.01 | 0.14 | 0.098 | 2.5 | 4.9 | - | |
2026.01 | 0.144 | 0.102 | 2.47 | 5.2 | - | |
2026.01 | 0.148 | 0.106 | 2.49 | 5.8 | - | |
2026.01 | 0.148 | 0.105 | 2.46 | 5.7 | - | |
2026.01 | 0.155 | 0.109 | 2.45 | 6.2 | - |