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 18, 2026Mar 14, 2026Apr 7, 2026Apr 30, 2026May 24, 2026Jun 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
86
2026.03
85.8
85.8
2026.06
85.07
2026.03
83.4
2026.03
83.3
82.52
2026.06
82.4
2026.06
81.55
2026.03
81.1
2026.06
80.22
2026.06
79.37
2026.03
78.8
2026.06
78.28
2026.05
78
2026.06
77.67
2026.06
77.55
2026.03
77.4
2026.05
76.7
2026.03
75.4
2026.06
74.76
2026.03
74.5
2026.03
74.5
2026.05
74
2026.03
73.9
2026.05
72.7
2026.03
72.6
2026.06
71.36
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