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

Multi-hop Question Answering on FRAMES (Accuracy)

86Accuracy

Coverage Anchor

10.39230.02149.6569.279Jan 26, 2026Feb 14, 2026Mar 5, 2026Mar 24, 2026Apr 12, 2026May 1, 2026May 21, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.03
86
2026.03
85.8
2026.03
83.4
2026.03
83.3
2026.03
81.1
2026.03
78.8
2026.05
78
2026.03
77.4
2026.05
76.7
2026.03
75.4
2026.03
74.5
2026.03
74.5
2026.05
74
2026.03
73.9
2026.05
72.7
2026.03
72.6
2026.05
65.3
2026.03
63.1
2026.05
57.3
2026.05
56
2026.05
56
2026.05
53.3
2026.05
50.7
2026.01
50
2026.05
50
2026.05
50
2026.01
45.9
2026.01
32.3
2026.03
29.4
2026.01
26.2
2026.01
25
2026.01
23.8
2026.01
21.5
2026.01
13.3