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

Multi-Hop Question Answering on 2WikiMultiHopQA (test val)

43.9Exact Match (EM)

DeepControl

21.0226.9632.938.84Feb 2, 2026Feb 27, 2026Mar 25, 2026Apr 20, 2026May 16, 2026Jun 11, 2026Jul 7, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2026.02
43.947.9---
2026.02
37.141.1---
2026.07
35.3---38
2026.07
35.1---39.2
2026.07
34.7---37.9
2026.07
34.3---37
2026.07
31.5---35.2
2026.07
31---33.5
2026.07
30.8---33.5
2026.07
30.7---33.5
2026.07
28.7---33.2
2026.07
28.5---31.2
2026.07
28.4---30.9
2026.07
25.1---27.7
2026.07
24.1---26.7
2026.07
21.9---24.3
2026.06
--31.430.2-
2026.06
--48.129.6-
2026.06
--4726.9-
2026.06
--50.541.7-
2026.06
--54.738.4-
2026.06
--54.739.3-
2026.06
--65.560.4-
2026.06
--67.359.1-
2026.06
--62.255.4-
2026.06
--69.664.2-
2026.06
--68.864.1-
2026.06
--66.369.1-
2026.06
--69.272.3-