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

Logical Reasoning on DetectiveQA

88.31Accuracy (DetectiveQA)

CDS

70.078874.811979.54584.2781May 13, 2026
Updated 20d ago

Evaluation Results

MethodLinks
2026.05
88.31
2026.05
88.31
2026.05
86.36
2026.05
85.71
2026.05
85.71
2026.05
85.06
2026.05
83.77
2026.05
83.12
2026.05
82.47
2026.05
81.17
2026.05
80.52
2026.05
80.52
2026.05
77.29
2026.05
76.63
2026.05
76.62
2026.05
75.97
2026.05
75.32
2026.05
75.32
2026.05
75.32
2026.05
75.32
2026.05
74.03
2026.05
73.38
2026.05
72.73
2026.05
70.78