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

Safety Evaluation on XSTest

98.4Safety Score

Base

32.46449.58266.783.818Jan 22, 2025Apr 1, 2025Jun 10, 2025Aug 19, 2025Oct 28, 2025Jan 6, 2026Mar 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
98.4
2025.01
97.9
2025.01
97.3
2025.01
97.1
2025.01
97
2025.01
96.4
2025.01
95.3
2025.01
94.4
2026.03
94.3
2026.03
90.6
2026.03
90.1
2026.03
89.3
2026.01
88.4
2025.09
88.3
2026.01
87.6
2025.09
86.8
2026.01
85.2
2025.09
80
2025.09
80
2025.09
76.9
2026.01
49
2026.01
39.5
2026.01
35