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

Multi-hop Reasoning on MuSiQue (Accuracy)

39.6Accuracy

AoT

33.25634.90336.5538.197Mar 13, 2026
Updated 11d ago

Evaluation Results

MethodLinks
2026.03
39.6
2026.03
39.4
2026.03
39.2
2026.03
39.1
2026.03
38.4
2026.03
38.4
2026.03
38.2
2026.03
38.1
2026.03
37.9
2026.03
37.8
2026.03
37.8
2026.03
37
2026.03
36.7
2026.03
36.5
2026.03
36.4
2026.03
36.2
2026.03
35.8
2026.03
35.8
2026.03
35.1
2026.03
35.1
2026.03
35
2026.03
34.2
2026.03
34.1
2026.03
34
2026.03
33.8
2026.03
33.6
2026.03
33.5