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

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

39.12SubEM

Stable-RAG

18.756824.043429.3334.6166Jan 6, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
39.1240.16
2026.01
38.9139.87
2026.01
36.8942.94
2026.01
35.7341.78
2026.01
35.1240.69
2026.01
34.3636.97
2026.01
33.7239.11
2026.01
33.5836.12
2026.01
33.5439.06
2026.01
33.1438.66
2026.01
32.9838.21
2026.01
32.7739.39
2026.01
32.7335.79
2026.01
31.7735.78
2026.01
31.4635.34
2026.01
30.7334.08
2026.01
30.4132.12
2026.01
30.1733.65
2026.01
30.1533.26
2026.01
29.4831.68
2026.01
29.0733.43
2026.01
28.5529.31
2026.01
28.3634.15
2026.01
27.2531.58
2026.01
27.2133.75
2026.01
26.9630.36
2026.01
26.8333.06
2026.01
26.5331.88
2026.01
26.4528.91
2026.01
26.3528.79
2026.01
26.1731.33
2026.01
26.1228.57
2026.01
25.9331.02
2026.01
25.6628.22
2026.01
25.3529.77
2026.01
24.6329.85
2026.01
21.3922.87
2026.01
21.3922.87
2026.01
19.5424.86
2026.01
19.5424.86