Multi-document Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
57.67HotpotQA Acc
45
May 19, 2026
72.6Accuracy @ 0% Threshold
18
Jun 29, 2026
72.6Recall@1
16
Feb 26, 2026
67.78HotpotQA Accuracy
14
Apr 21, 2026
44.8Rouge-L
10
Feb 26, 2026
45Accuracy
9
May 15, 2026
68Average Score
8
May 21, 2026
60.3Accuracy
7
Jul 2, 2026
0.876Hypervolume
4
Mar 12, 2026