Open-domain Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.401F1
111
May 26, 2026
83.8Accuracy
103
Jun 11, 2026
76.1EM
88
May 29, 2026
60.7Exact Match (EM)
82
May 14, 2026
72.6Exact Match
80
Feb 26, 2026
91Accuracy
78
Jun 11, 2026
61.6Accuracy
74
Jun 11, 2026
73.3EM
59
May 11, 2026
35.8F1
57
Apr 27, 2026
62.6F1 Score
57
Apr 27, 2026
72.4F1 Score
57
Apr 27, 2026
57.8Exact Match (EM)
55
Feb 26, 2026
58.15Accuracy
44
Jun 11, 2026
74.01SubEM
40
Feb 26, 2026
52.88SubEM
40
Feb 26, 2026
44.38EM
39
May 29, 2026
56.6Exact Match
39
Feb 26, 2026
48.7Exact Match
38
Feb 26, 2026
33.71EM
37
Feb 26, 2026
60.4EM
37
Feb 26, 2026
59.15Accuracy
36
Feb 26, 2026
51.4EM
33
Feb 26, 2026
63.9F1 Score
33
Feb 26, 2026
52.2F1 Score
31
Jun 12, 2026
61.8Exact Match (EM)
30
Feb 26, 2026