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

Reading Comprehension on BoolQ (Accuracy)

88.47Accuracy (BoolQ)

FP

70.883675.449380.01584.5807Sep 22, 2025Nov 3, 2025Dec 16, 2025Jan 27, 2026Mar 11, 2026Apr 22, 2026Jun 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
88.47
2026.06
88.38
2026.06
88.29
2026.05
88.07
2026.06
87.98
2026.06
87.98
2026.06
87.89
2026.05
87.68
2026.05
87.22
2026.06
87.07
2026.06
86.92
2026.05
86.76
2026.04
86.23
2026.05
86.2
2026.04
86.09
2026.06
85.99
2026.05
85.9
2026.05
85.75
2026.04
85.6
2026.04
85.57
2026.05
85.4
2026.04
85.14
2026.04
85.05
2026.04
84.92
2026.04
84.8
2026.05
84.71
2026.06
84.68
2026.04
84.04
2026.03
83.98
2026.05
83.85
2026.04
83.67
2026.05
83.6
2026.04
83.15
2026.04
83.15
2026.05
82.6
2026.05
82.35
2026.05
82.11
2026.05
82.11
2026.05
82.02
2026.05
82.02
2026.04
81.93
2026.05
81.9
2026.05
81.25
2026.04
81.11
2026.05
81.07
2026.05
81.04
2026.04
80.61
2026.05
80.61
2026.05
80.5
2026.04
80.12
2026.05
80.12
2026.04
80
2026.04
79.63
2026.05
79.27
2026.04
79.15
2025.09
78.91
2026.04
78.65
2026.04
78.53
2026.05
78.47
2026.05
78.38
2025.09
78.12
2026.05
77.49
2026.05
76.7
2026.05
76.57
2025.09
76.56
2026.05
76.39
2026.05
76.2
2026.05
76.02
2026.05
75.84
2026.05
75.78
2026.05
75.72
2026.05
75.53
2026.05
75.2
2025.09
75
2026.04
74.5
2026.04
74.28
2026.05
74.07
2026.05
73.91
2026.05
73.76
2026.04
73.64
2026.04
73.49
2026.05
73.24
2026.05
73.21
2026.04
73.1
2026.05
72.94
2026.05
72.66
2026.05
72.66
2026.05
72.63
2026.04
72.51
2026.05
72.35
2026.05
72.3
2026.04
72.26
2026.04
72.23
2026.05
72.23
2026.05
72.14
2026.05
71.99
2026.05
71.77
2026.05
71.62
2026.05
71.56
2026.05
71.56
Showing 100 of 258 rows