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

Multi-hop QA on 2Wiki

62EM

HELP

-2.45414.2792531.012547.74575Oct 1, 2025Oct 25, 2025Nov 18, 2025Dec 13, 2025Jan 6, 2026Jan 30, 2026Feb 24, 2026
Updated 9d ago

Evaluation Results

MethodLinks
2026.02
6269.5
2026.02
60.269.4
2026.02
45.558.6
2026.02
42.453.2
2025.10
41.4-
2025.10
38.2-
2025.10
35.2-
2025.10
31.9-
2025.10
30-
2025.10
29.8-
2025.10
29.2-
2025.10
27.5-
2025.10
25-
2025.10
24.4-
2025.10
23.5-
2025.10
22.6-
2025.10
21.8-
2025.10
17.6-
2025.10
11.1-
2025.10
2.1-
2025.12
0.7170.79
2025.12
0.7170.792
2025.12
0.7120.788
2025.12
0.70.781
2025.12
0.650.718
2025.12
0.650.71
2025.12
0.6110.683
2025.12
0.6050.697
2025.12
0.5960.679
2025.12
0.5940.673
2025.12
0.5750.615
2025.12
0.5580.606
2025.12
0.5510.6
2025.12
0.5140.586
2025.12
0.4920.528
2025.12
0.4790.512
2025.12
0.4730.521
2025.12
0.4570.61
2025.12
0.3970.484
2025.12
0.3810.419
2025.12
0.0940.116
2025.12
0.0250.121
2026.05
-57.8
2026.05
-60.5
2026.05
-62.1
2026.05
-64.7