Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Harmful-input detection on Safety Evaluation Suite (AEG, AEG2, HB-A, HB-V, OAI, SAL, SST, Toxic, WGT, WJB)

89.8AEG Score

WildGuard

65.8872.0978.384.51Jun 26, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.06
89.881.692.299.172.79799.570.788.797.888
2026.06
8880.793.198.568.994.199.555.580.183.781.6
2026.06
87.88191.699.168.897.69964.58288.685.3
2026.06
87.581.492.999.465.298.610060.880.288.484.7
2026.06
86.582.590.198.769.898.599.566.677.990.786
2026.06
86.282.279.79976.164.99978.8828875.2
2026.06
85.477.392.598.564.896.697.143.781.285.479.8
2026.06
82.483.989.197.476.396.499.580.48294.388.8
2026.06
77.876.983.298.168.658.195.954.380.188.566.4
2026.06
7682.783.698.780.893.297.482.486.791.287.7
2026.06
75.778.386.494.173.788.79858.479.988.879.7
2026.06
74.174.156.589.654.343.788.540.461.448.350.6
2026.06
72.873.466.686.455.132.288.936.166.860.647
71.777.184.698.17945.599.553.976.867.959.9
2026.06
69.272.577.197.251.639.394.942.97257.451.4
2026.06
68.47176.697.553.841.593.842.372.655.251.9
67.871.585.295.773.566.498.551.573.869.666.6
2026.06
66.871.473.797.857.32791.448.369.851.547