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

Safety and Helpfulness Evaluation on Beavertails

92.03Safety Score

SAFER-STEER

26.634843.612460.5977.5676Mar 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
92.0386.83
2026.03
88.8985.97
2026.03
88.8186.1
2026.03
86.9582.88
2026.03
85.5977.8
2026.03
80.8577.76
2026.03
80.8176.36
2026.03
79.1573.73
2026.03
76.7875.93
2026.03
76.4481.19
2026.03
68.5473.03
2026.03
55.9358.98
2026.03
49.4955.59
2026.03
47.1854.19
2026.03
46.138.81
2026.03
35.3141.93
2026.03
32.5436.95
2026.03
29.1524.07