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

Multi-Hop Question Answering on HotpotQA (SubEM, F1)

58.9F1

GraphRAG-Router

21.428831.156940.88550.6131Jan 6, 2026Jan 20, 2026Feb 3, 2026Feb 17, 2026Mar 3, 2026Mar 17, 2026Mar 31, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
58.9-
2026.03
50.1-
2026.03
48.7-
2026.03
46.8-
2026.03
46.7-
2026.03
44.5-
2026.03
43.9-
2026.03
43.6-
2026.01
42.9436.89
2026.03
42.5-
2026.01
41.7835.73
2026.03
40.9-
2026.01
40.6935.12
2026.01
40.1639.12
2026.01
39.8738.91
2026.01
39.3932.77
2026.01
39.1133.72
2026.01
39.0633.54
2026.03
38.8-
2026.01
38.6633.14
2026.01
38.2132.98
2026.03
37.6-
2026.03
37.1-
2026.01
36.9734.36
2026.01
36.1233.58
2026.03
36.1-
2026.01
35.7932.73
2026.01
35.7831.77
2026.01
35.3431.46
2026.01
34.1528.36
2026.01
34.0830.73
2026.01
33.7527.21
2026.01
33.6530.17
2026.01
33.4329.07
2026.01
33.2630.15
2026.01
33.0626.83
2026.01
32.1230.41
2026.01
31.8826.53
2026.01
31.6829.48
2026.01
31.5827.25
2026.01
31.3326.17
2026.01
31.0225.93
2026.01
30.3626.96
2026.01
29.8524.63
2026.01
29.7725.35
2026.01
29.3128.55
2026.01
28.9126.45
2026.01
28.7926.35
2026.01
28.5726.12
2026.01
28.2225.66
2026.01
24.8619.54
2026.01
24.8619.54
2026.01
22.8721.39
2026.01
22.8721.39