Multi-hop QA
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
34.4Accuracy
6
Jun 5, 2026
17.4Accuracy
6
Jun 5, 2026
37Accuracy
6
Jun 5, 2026
37.6Accuracy
6
Jun 5, 2026
30.4Pass@1
6
Apr 10, 2026
36pass@1
6
Apr 10, 2026
33.5pass@1
6
Apr 10, 2026
66.7nLCS
5
Mar 4, 2026
53.61F1 Score
5
Mar 4, 2026
72F1 Score
4
May 25, 2026
0.83Avg Violation
4
Apr 10, 2026
0.56Average Violation
4
Apr 10, 2026
81.5Pass@1 Accuracy
4
Mar 4, 2026
10.5EM
3
Feb 26, 2026
38.58Token F1
2
Jun 1, 2026
37.19Token F1
2
Jun 1, 2026