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

Boolean Question Answering on BoolQ (Accuracy)

88.91Accuracy

Qwen 3

35.786849.578463.3777.1616Aug 20, 2025Oct 11, 2025Dec 2, 2025Jan 24, 2026Mar 17, 2026May 8, 2026Jun 30, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2026.05
88.91
2026.06
88.7
2026.05
88.43
2026.06
88.2
2026.04
88
2026.06
88
2026.04
87.9
2026.04
87.6
2026.04
87.4
2026.05
85.74
2026.06
84.43
2026.06
84.22
2026.06
84.22
2026.04
84.1
2026.06
83.7
2026.06
83.36
2026.04
83.1
2026.06
83.09
2026.06
82.87
2026.06
82.4
2026.04
81.5
2026.04
80.5
2026.06
79.57
2026.06
79.54
2026.06
79.36
2026.06
79.2
2026.06
78.93
2026.06
78.6
2026.04
77.8
2026.04
77.5
2026.04
77.4
2026.04
77.2
2026.06
77.12
2026.06
76.67
2026.04
76.6
2026.06
76.57
2026.04
76.2
2026.04
75.9
2026.06
75.35
2026.06
75.08
2026.06
74.86
2026.04
74.4
2026.04
72.1
2026.04
71.3
2026.06
69.37
2026.06
69.05
2026.06
68.41
2026.06
63.55
2026.04
62.8
2026.04
62.7
2026.05
60.21
2025.08
56.18
2026.05
49.42
2026.06
40.55
2026.06
38.5
2025.08
37.83