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

Factual Knowledge on BoolQ

87.7Accuracy

ORACLE

35.835249.300162.76576.2299Mar 6, 2024Jul 8, 2024Nov 9, 2024Mar 14, 2025Jul 16, 2025Nov 17, 2025Mar 22, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.03
87.7
2026.03
87.5
2026.03
86.8
2026.03
86.3
2026.03
86.2
2026.03
85.6
2026.03
85
2026.03
84.7
2026.03
84.4
2026.03
83.8
2026.03
83.2
2026.03
83.1
2026.03
83
2026.03
82.8
2026.03
82.5
2024.03
82.39
2026.03
82.1
2024.10
80.9
2026.03
80.9
2026.03
80.5
2024.10
77.6
2024.10
76.6
2024.03
74.71
2024.03
74.1
2024.10
72.2
2024.03
71.62
2024.03
67.83
2024.10
66
2024.03
65.6
2024.03
64.07
2024.03
63.98
2024.03
62.54
2024.03
62.48
2024.03
62.35
2024.03
61.19
2024.10
61.1
2024.03
56.54
2024.03
56.42
2024.03
56.15
2024.03
55.2
2024.03
39.3
2024.03
38.32
2024.03
37.86
2024.03
37.83