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

Personalization on Multi-Bench (MB)

94.84Win Rate

MIPO

12.305633.732855.1676.5872Mar 10, 2026
Updated 27d ago

Evaluation Results

MethodLinks
2026.03
94.84
2026.03
93.65
2026.03
93.65
2026.03
93.26
2026.03
91.67
2026.03
90.48
2026.03
90.48
2026.03
90.08
2026.03
88.89
2026.03
84.12
2026.03
83.33
2026.03
82.93
2026.03
82.22
2026.03
79.76
2026.03
78.97
2026.03
78.57
2026.03
77.78
2026.03
77.38
2026.03
76.19
2026.03
75
2026.03
74.6
2026.03
74.6
2026.03
73.81
2026.03
73.02
2026.03
72.62
2026.03
72.62
2026.03
72.62
2026.03
72.22
2026.03
70.64
2026.03
70.24
2026.03
66.67
2026.03
64.68
2026.03
64.29
2026.03
63.1
2026.03
59.52
2026.03
59.52
2026.03
47.62
2026.03
46.43
2026.03
39.68
2026.03
39.29
2026.03
39.29
2026.03
36.9
2026.03
35.31
2026.03
34.52
2026.03
15.48