Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multi-hop Question Answering on LoCoMo

48.35F1

Membox

3.26614.970526.67538.3795Jan 7, 2026Jan 13, 2026Jan 19, 2026Jan 26, 2026Feb 1, 2026Feb 7, 2026Feb 14, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.01
48.3535.1----
2026.01
46.35--33.82--
2026.01
46.28--39.65--
45.935.676.6---
2026.01
44.86--32.44--
2026.01
44.2-77.233.7--
2026.02
42.833.778.7---
2026.01
42.8-76.233--
2026.01
42.5730.92----
2026.02
41.731.975.1---
2026.02
41.732.178.4---
2026.02
41.532.571---
2026.01
41.5-7132.5--
2026.01
41.17--33.06--
2026.01
40.97--29.36--
2026.01
40.1-68.230.3--
2026.01
39.8826.39----
2026.01
39.75--28.92--
2026.01
39.52--28.22--
2026.01
38.7227.13----
2026.01
38.6--26.54--
2026.01
37.41--25.9--
2026.01
37.17--25.74--
2026.01
37.06--24.96--
2026.01
36.8326.5----
2026.01
34.13--26.02--
2026.01
32.97--21.93--
2026.01
32.8623.76----
2026.02
32.623.662.4---
2026.02
32.422.255.7---
2026.01
32-58.937.1--
31.97--31.85-3.22
2026.01
31.6623.34----
2026.02
30.520.453.7---
2026.01
30.5-53.720.4--
2026.01
30.36--22.83--
2026.01
30.3622.83----
2026.01
30.28--25.49--
2026.02
30.11--30.91-2.56
2026.02
28.61--26.81-1.79
2026.01
28.33--21.63--
2026.01
28.03--19.95--
2026.01
28--18.47--
2026.01
2818.47----
2026.01
27.1--21.45--
2026.01
27.0820.46----
2026.01
27.0220.09----
2026.01
26.81--20.45--
2026.01
26.65--17.72--
2026.01
26.6517.72----
2026.01
25.02--19.75--
2026.01
25.0219.75----
2026.01
21.5--15.2--
2026.01
20.1--15--
2026.01
20.1-31.712.8--
2026.01
14.61--9.95--
2026.01
14.619.95----
2026.02
12.97--12.81-1.85
2026.01
9.15--6.48--
2026.01
9.156.48----
2026.02
9.11--8.82-1.06
2026.01
6.49--4.69--
2026.01
6.494.69----
2026.02
6.02--5.89-1.12
2026.02
5.44--5.03-1.01
2026.01
5--4.77--
2026.01
54.77----