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

Gender bias evaluation on Pronoun Change

99.66Performance Score (P)

PRISM-∆

36.42852.84469.2685.676Mar 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
99.6699.56
2026.03
99.6699.56
2026.03
99.4899.34
2026.03
99.499.3
2026.03
98.8698.72
2026.03
98.8698.68
2026.03
98.6698.54
2026.03
98.5698.26
2026.03
98.4298.22
2026.03
98.197.84
2026.03
9897.84
2026.03
97.9497.46
2026.03
97.797.24
2026.03
96.1894.6
2026.03
96.0694.52
2026.03
95.8294.64
2026.03
95.7896.42
2026.03
95.7693.88
2026.03
95.1893.26
2026.03
94.5494.42
2026.03
93.9294.96
2026.03
93.1490.52
2026.03
91.692.2
2026.03
90.9890.94
2026.03
90.1691.68
2026.03
89.0890.58
2026.03
86.4184.99
2026.03
81.5381.11
2026.03
80.2778.19
2026.03
76.0574.45
2026.03
72.6174.95
2026.03
68.4768.01
2026.03
67.3966.43
2026.03
41.3435.25
2026.03
38.8632.45