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

Safety Evaluation on ANTHROPIC HH (test)

88.85Safety Score

TOSS-Pro

46.36657.395568.42579.4545Mar 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
88.85-
2026.03
88.82-
2026.03
86.98-
2026.03
83.22-
2026.03
78.54-
2026.03
67.38-
2026.03
66.49-
2026.03
66.03-
2026.03
64.17-
2026.03
63.7-
2026.03
58.94-
2026.03
58.57-
2026.03
58.2-
2026.03
56.89-
2026.03
55.29-
2026.03
52.5-
2026.03
51.49-
2026.03
51.15-
2026.03
50-
2026.03
50-
2026.03
50-
2026.03
50-
2026.03
48.16-
2026.03
48-
2026.03
-3.02
2026.03
-2.99
2026.03
-3.03
2026.03
-3.28
2026.03
-2.94
2026.03
-2.61
2026.03
-2.5
2026.03
-2.99
2026.03
-3.08
2026.03
-2.93
2026.03
-3.04
2026.03
-2.83
2026.03
-2.49
2026.03
-2.14