Single-hop Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
73.6EM
200
Jul 8, 2026
72EM
147
Jul 8, 2026
0.641F1
111
May 26, 2026
51.7Exact Match (EM)
60
May 19, 2026
66Accuracy
60
Jul 7, 2026
51.5Accuracy
43
Jul 7, 2026
49.1Accuracy
37
May 14, 2026
59.61F1 Score
35
Mar 19, 2026
47.5EM
33
Mar 5, 2026
68.1Exact Match
30
Mar 19, 2026
50.45F1 Score
24
Jul 3, 2026
52.4Accuracy
24
Jun 5, 2026
37.9F1
24
Feb 26, 2026
48.9Accuracy
22
Jul 7, 2026
23.76Overall Score
22
Feb 26, 2026
44.79Score
22
Feb 26, 2026
23.89Score
22
Feb 26, 2026
45.83Score
22
Feb 26, 2026
45.3Accuracy
21
Feb 26, 2026
86.8F1 Score
21
Feb 26, 2026
31.45EM
20
Feb 26, 2026
68Accuracy
19
May 29, 2026
48.2Accuracy
19
May 29, 2026
31.36Score
17
Feb 26, 2026
45.1Score
17
Feb 26, 2026