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

Question Answering on HotpotQA (Acc)

90.38Accuracy

DMoA

21.240839.190457.1475.0896Mar 26, 2026Apr 3, 2026Apr 11, 2026Apr 20, 2026Apr 28, 2026May 6, 2026May 15, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.05
90.38
2026.05
90.04
2026.05
89.35
2026.05
88.29
2026.05
87.66
2026.05
87.22
2026.05
86.45
2026.05
85.4
2026.05
84.55
2026.05
84.28
2026.05
84.02
2026.05
83.52
2026.05
83.35
2026.05
83.25
2026.05
82.35
2026.05
82.24
2026.05
81.5
2026.05
81.04
2026.05
80.77
2026.03
43.56
2026.03
43.12
2026.03
42.33
2026.03
42.12
2026.03
41.99
2026.03
41.97
2026.03
41.13
2026.03
41.13
2026.03
32.12
2026.03
31.25
2026.03
31.04
2026.03
30.18
2026.03
29.82
2026.03
29.33
2026.03
28.73
2026.03
27.49
2026.03
24.28
2026.03
23.9