Single-hop Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
49.64NQ Accuracy
16
May 27, 2026
47.8Accuracy
15
Feb 26, 2026
47.2Accuracy
14
Mar 13, 2026
66.6Accuracy
14
Mar 13, 2026
50.2Accuracy
14
Mar 13, 2026
48.5NQ Score
13
Mar 20, 2026
49Set Accuracy
13
Feb 26, 2026
64Avg@4
9
Feb 26, 2026
61.4F1 Score
8
Feb 26, 2026
40.8Answer F1 Score
6
Feb 26, 2026
40.7F1 Score (Answer)
6
Feb 26, 2026
29.89Score
5
Feb 26, 2026
45.1Score
5
Feb 26, 2026
47.1EM
3
May 14, 2026
32.8Accuracy
2
Feb 26, 2026