Multi-hop Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
86.06Accuracy
5
Apr 9, 2026
72.1Accuracy
5
Apr 9, 2026
66.6Accuracy (Zero-Shot)
5
Apr 9, 2026
61.6LJFT Score
5
Feb 27, 2026
0.98Avg F1
5
Feb 26, 2026
100Avg F1
5
Feb 26, 2026
29.1F1 Score
5
Feb 26, 2026
35.65LJFT Score
5
Feb 27, 2026
47.72LJFT
5
Feb 27, 2026
23.6LJFT
5
Feb 27, 2026
9.69LJFT
5
Feb 27, 2026
59.5Accuracy
5
Feb 26, 2026
56.9EM
5
Feb 26, 2026
19.78Score
5
Feb 26, 2026
25.4Overall Score
5
Feb 26, 2026
15.1Score
5
Feb 26, 2026
79.8Accuracy
5
Feb 26, 2026
80F1 Score
4
Jun 15, 2026
37.6Evidence Score
4
May 25, 2026
10.3Evidence Score
4
May 25, 2026
33.2Evidence Score
4
May 25, 2026
34.7Mean F1
4
May 21, 2026
60.1Mean F1
4
May 21, 2026
47.3Mean F1
4
May 21, 2026
54.07EM
4
Apr 15, 2026