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

Question Answering on BoolQ (Accuracy)

90.03Accuracy

ShortGPT

62.750869.832976.91583.9971Jun 17, 2025Aug 18, 2025Oct 19, 2025Dec 20, 2025Feb 20, 2026Apr 23, 2026Jun 25, 2026
Updated 29d ago

Evaluation Results

MethodLinks
2026.05
90.03
2026.05
89.85
2026.05
89.66
2026.05
89.64
2026.05
89.6
2026.05
89.18
2026.05
89.14
2026.06
89.1
2026.05
88.07
2026.06
87.98
2026.06
87.86
2026.06
86.97
2026.06
86.9
2026.05
86.76
2026.05
86.76
2026.05
86.15
2026.06
85.81
2026.05
85.23
2026.05
85.05
2026.05
85.02
2025.11
84.83
2026.06
84.83
2025.11
84.79
2025.11
84.7
2025.11
84.6
2026.06
84.43
2026.06
83.98
2026.06
83.88
2025.11
83.6
2025.11
83.55
2025.11
83.4
2026.06
83.36
2026.06
83.09
2026.06
83.03
2026.05
82.81
2025.11
82.69
2025.11
82.5
2025.11
82.32
2025.11
82.11
2025.11
81.9
2025.11
81.84
2025.11
81.44
2026.06
80.61
2025.11
80.58
2026.05
80.55
2025.11
80.52
2026.06
80.31
2026.06
80.28
2026.05
80.09
2025.06
79.37
2025.11
79.15
2026.05
78.32
2025.11
77.89
2026.06
77.8
2025.11
77.74
2026.05
77.71
2026.06
77.13
2025.11
76.97
2025.11
76.94
2026.05
76.57
2025.11
75.99
2025.11
75.9
2026.06
75.63
2025.11
75.5
2026.05
75.2
2025.11
75.05
2025.11
75.02
2025.06
74.46
2026.06
74.43
2025.08
73.4
2026.05
72.63
2025.11
72.29
2025.11
72.05
2025.06
71.25
2025.11
71.22
2025.11
70.55
2025.10
69
2026.06
68.66
2026.06
68.1
2026.05
67.09
2026.05
66.69
2026.05
66.3
2025.10
66
2026.06
65.93
2026.05
65.9
2026.05
65.2
2026.05
64.92
2026.06
64.71
2025.08
64.7
2026.05
64.59
2026.05
64.5
2026.05
64.5
2025.11
64.34
2025.11
64.28
2026.05
64.2
2026.06
64.04
2025.08
64
2026.06
63.9
2026.05
63.82
63.8
Showing 100 of 233 rows