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

Multi-hop QA on 2WikiMultihopQA

56.4Exact Match (EM)

SDGA-Phase

-0.59214.2042943.796Feb 28, 2026Mar 12, 2026Mar 24, 2026Apr 5, 2026Apr 17, 2026Apr 29, 2026May 12, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
56.4---
2026.05
55.8---
2026.03
55.563.6--
2026.02
53.862.350.930.32
2026.03
52.3---
2026.03
51.866.2--
2026.05
51.8---
2026.02
50.259.170.370.15
2026.05
49.5---
2026.05
47.8---
2026.03
45.965.6--
2026.03
45.6---
43.951.441.240.34
2026.03
43.5---
2026.05
43.2---
2026.03
42.7---
2026.05
42.6---
2026.03
42.151.5--
2026.02
41.950.070.550.28
2026.05
41.6---
2026.05
41.2---
2026.03
40.7---
2026.05
38---
2026.05
37.6---
2026.03
37.4---
2026.05
37.3---
2026.05
37.1---
2026.05
37.1---
2026.05
36.8---
2026.05
36.8---
2026.05
36.6---
2026.02
35.945.211.120.29
2026.03
34.8---
2026.05
33.7---
2026.03
33.6---
2026.03
32.7---
2026.05
32.6---
2026.05
32.5---
2026.05
32.4---
2026.03
31.8---
2026.03
30.938.5--
2026.05
30.6---
2026.03
30.537.8--
2026.03
29.5---
2026.03
29.3---
2026.05
28.7---
2026.05
27.6---
2026.03
26.9---
2026.05
26.8---
2026.03
25.132.1--
2026.05
24.7---
2026.03
24.537.2--
2026.05
24.2---
2026.03
23---
2026.03
22.729.1--
2026.03
20.526.2--
2026.03
19.738.2--
2026.05
18.3---
2026.03
16.723.9--
2026.05
16.4---
2026.05
15.7---
2026.03
15.319.6--
2026.03
14.921.3--
2026.03
13.547.7--
2026.03
12.630.1--
2026.03
10.815.1--
2026.03
1.61.9--