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

Safety Evaluation on Manual Evaluation Safety Dataset

3.83Average Safety Score

M_Self-MOA

2.03082.49792.9653.4321Mar 7, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
3.83
2026.03
3.8
2026.03
3.67
2026.03
3.67
2026.03
3.37
2026.03
3.3
2026.03
3.2
2026.03
2.97
2026.03
2.77
2026.03
2.43
2026.03
2.13
2026.03
2.1