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

Question Answering on SQuAD KRE-curated version (EM/F1)

72.6F1 Score

AdaCAD

4.06421.85739.6557.443Oct 14, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.10
72.667.4
2025.10
71.555.7
2025.10
69.755.2
2025.10
69.453.4
2025.10
69.252.1
2025.10
68.453.3
2025.10
68.153.6
2025.10
6750.3
2025.10
66.451.2
2025.10
66.250.2
2025.10
6647.7
2025.10
65.449.7
2025.10
64.546
2025.10
64.445.8
2025.10
64.248.5
2025.10
63.844.9
2025.10
63.846.1
2025.10
63.844.9
2025.10
63.644.5
2025.10
61.643.6
2025.10
61.350.2
2025.10
60.341.8
2025.10
60.340.1
2025.10
60.243.8
2025.10
59.843.7
2025.10
59.239.7
2025.10
58.137.4
2025.10
57.842.5
2025.10
56.637.6
2025.10
56.437.5
2025.10
52.633.9
2025.10
51.432.1
2025.10
48.629.7
2025.10
8.91.2
2025.10
8.11
2025.10
6.70.4