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

In-context retrieval on DROP

88.6Accuracy

BERT-Judge

11.6431.6251.671.58Mar 15, 2026Mar 19, 2026Mar 23, 2026Mar 28, 2026Apr 1, 2026Apr 5, 2026Apr 10, 2026
Updated 6d ago

Evaluation Results

MethodLinks
2026.04
88.6
2026.04
77
2026.04
69.3
2026.03
28.2
2026.03
27.2
2026.03
26.8
2026.03
26.4
2026.03
26.4
2026.03
26.3
2026.03
26
2026.03
25.6
2026.03
24.9
2026.03
22.9
2026.03
19.5
2026.03
17.2
2026.03
14.6