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

Multi-hop Question Answering on 2WikiMultiHopQA Out-Of-Distribution (OOD)

74.2Accuracy

QwenLong-L1-32B

-2.96817.06637.157.134Sep 27, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
74.2
2025.09
71.9
2025.09
69.5
2025.09
67.2
2025.09
67.2
2025.09
65.6
2025.09
63.9
2025.09
63.1
2025.09
62.5
2025.09
60.9
2025.09
60.9
2025.09
59.4
2025.09
58.6
2025.09
58.6
2025.09
57.8
2025.09
57.8
2025.09
57
2025.09
56.3
2025.09
56.3
2025.09
55.6
2025.09
54.7
2025.09
54.5
2025.09
53.5
2025.09
53.1
2025.09
52.3
2025.09
51.6
2025.09
50.4
2025.09
50.3
2025.09
49.2
2025.09
49.2
2025.09
48.9
2025.09
47.7
2025.09
47.7
2025.09
46.1
2025.09
45.4
2025.09
45.3
2025.09
45.3
2025.09
43
2025.09
42.5
2025.09
42.2
2025.09
41.7
2025.09
38.3
2025.09
37.8
2025.09
37
2025.09
36.7
2025.09
36.2
2025.09
35.4
2025.09
34.4
2025.09
32
2025.09
32
2025.09
31.3
2025.09
29.9
2025.09
29.7
2025.09
29.7
2025.09
28.1
2025.09
28.1
2025.09
28.1
2025.09
26.6
2025.09
25.8
2025.09
25.8
2025.09
25.8
2025.09
25.8
2025.09
25
2025.09
24.6
2025.09
21.1
2025.09
2.3
2025.09
2.3
2025.09
0.8
2025.09
0.8
2025.09
0
2025.09
0
2025.09
0