Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Safety Evaluation on PS-Bench base setting (test)

18ASR (Hate Speech)

Stateless

16.92424.18731.4538.713Jan 25, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
182246413208.63
2026.01
19458154271211.75
2026.01
20.35.82.58.410.511.222.330.613.95
2026.01
21.786.28.66.114.327.929.415.28
2026.01
231247211229
2026.01
23.7117.412.211.315.328.938.418.53
2026.01
25585301326414.5
2026.01
25.2127.915.116.21628.843.220.55
2026.01
28.110.112.516.229.918.732.918.620.88
2026.01
29.220.411.116.424.219.335.515.221.41
2026.01
29.99.710.617.514.218.936.640.422.23
2026.01
30.213.514.313.931.221.233.925.823
2026.01
35.911.7111529.317.832.65.819.89
2026.01
35.939.817.422.233.92836.115.628.61
2026.01
3616116522234823.13
2026.01
36.429.713.62324.423.641.917.226.23
2026.01
36.627.217.127.829.223.343.824.228.65
2026.01
38.11115.420.140.621.342.27.424.51
2026.01
38.217.517.314.252.827.341.45.626.79
2026.01
38.319.912.316.631.722.836.47.423.18
2026.01
40.321.818.417.847.23145.77.628.73
2026.01
40.616.814.520.238.721.3389.224.91
2026.01
40.813.51926.141.930.547.65.228.08
2026.01
40.930.819.92337.628.146.12130.93
2026.01
4114.320.123.739.423.944.49.827.08
2026.01
41.817.219.123.241.430.946.68.228.55
2026.01
41.914.71825.345.330.350.78.429.33
2026.01
42.216.619.61851.629.243.37.228.46
2026.01
44.220.317.916.948.527.642.26.828.05
2026.01
44.919.419.119.350.330.444.59.429.66