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

Object Hallucination on POPE

91.9F1 Score

CALRD

79.31682.58385.8589.117May 20, 2026May 24, 2026May 29, 2026Jun 2, 2026Jun 7, 2026Jun 11, 2026Jun 16, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.06
91.9-
2026.06
91.6-
2026.06
91.4-
2026.06
91.2-
2026.06
91.2-
2026.06
90.6-
2026.05
89.6289.8
2026.06
89.3-
2026.05
89.1589.45
2026.05
89.0888.92
2026.05
88.9189.27
2026.06
88.9-
2026.05
88.8289.19
2026.06
88.7-
2026.06
88.6-
2026.06
88.6-
2026.05
88.5188.69
2026.06
88.5-
2026.06
88.3-
2026.06
88.2-
2026.05
87.9588.31
2026.06
87.9-
2026.05
87.8188.16
2026.06
87.6-
2026.06
87.5-
2026.06
87.5-
2026.06
87.3-
2026.06
87.1-
2026.06
87.1-
2026.06
86.9-
2026.06
86.7-
2026.05
86.3885.63
2026.05
86.1285.76
2026.06
85.9-
2026.05
85.8784.82
2026.06
85.6-
2026.05
85.5485.13
2026.06
85.5-
2026.05
85.4584.74
2026.05
85.485.41
2026.06
85.4-
2026.06
85.4-
2026.06
85.4-
2026.05
85.3184.74
2026.05
85.2884.6
2026.05
85.2284.5
2026.05
85.0684.19
2026.06
84.9-
2026.06
84.9-
2026.06
84.9-
2026.06
84.8-
2026.06
84.8-
2026.06
84.7-
2026.06
84.5-
2026.05
84.4383.03
2026.06
84.4-
2026.06
83.8-
2026.06
83.4-
2026.06
83.4-
2026.06
83.2-
2026.06
83.1-
2026.06
83.1-
2026.06
82.6-
2026.06
82.3-
2026.06
82.2-
2026.06
82.1-
2026.06
81.9-
2026.06
81.8-
2026.06
81.4-
2026.06
81.4-
2026.06
81.3-
2026.06
80.9-
2026.06
80.8-
2026.06
80.8-
2026.06
80.8-
2026.06
80.7-
2026.06
80-
2026.06
79.9-
2026.06
79.8-
2026.05
-88.54
2026.05
-87
2026.05
-87.01
2026.05
-86.54
2026.05
-86.28
2026.05
-87.1
2026.05
-87.68
2026.05
-85.27
2026.05
-86.83
2026.05
-86.92
2026.05
-87.54
2026.05
-86.5
2026.05
-78.09
2026.05
-84.74
2026.05
-86.77
2026.05
-87.12
2026.05
-90.51
2026.05
-89.68
2026.05
-88.94
2026.05
-89.77
2026.05
-89.82
Showing 100 of 134 rows