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

Prompt Harmfulness Classification on Public Prompt Harmfulness Benchmarks Suite

74.7ToxiC Score

EXPGUARD

23.42836.73950.0563.361Jun 26, 2024Oct 6, 2024Jan 17, 2025Apr 29, 2025Aug 10, 2025Nov 20, 2025Mar 3, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
74.777.383.792.999.285.786.1
7374.782.99970.580-
2026.03
72.574.781.180.370.575.171.5
2024.06
70.872.189.499.598.986.1-
2026.03
70.77280.894.598.784.288.7
2026.03
70.267.581.277.777.775.578.5
7067.584.810077.780-
2024.06
68.370.584.410010084.6-
2026.03
6779.272.280.859.868.451.4
61.675.874.19367.274.4-
2026.03
61.675.875.382.567.269.756
2026.03
57.680.646.367.15.348.131.7
2026.03
53.779.176.488.498.978.977
47.176.171.895.89477-
2026.03
47.176.17689.19475.570.9
2026.03
31.968.43228.54.927.91.8
2026.03
28.570.533.647.39.632.34.1
25.47931.9639.641.8-
2026.03
25.47936.257.69.636.712.1