Open-domain Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.418Accuracy
28
Mar 18, 2026
50.18Accuracy (Exact Match)
27
Jun 11, 2026
30.6Accuracy
26
Jun 11, 2026
77.1Accuracy
26
Feb 26, 2026
55.3Exact Match (EM)
26
Feb 26, 2026
53Exact Match
25
Feb 26, 2026
71.7F1
24
Apr 27, 2026
32.6F1 Score
24
Jul 3, 2026
15.12F1 Score
24
Feb 26, 2026
29Accuracy
20
Feb 26, 2026
81.4Accuracy
20
Jun 11, 2026
84.6Hits@1
19
Feb 26, 2026
11.4Macro EM
19
Feb 27, 2026
49Macro EM
19
Feb 27, 2026
48.78EM
18
Feb 26, 2026
74Accuracy (%)
17
May 29, 2026
51.5Exact Match
17
Feb 26, 2026
59.3EM
16
May 29, 2026
50.2EM
16
Feb 26, 2026
45.2Exact Match (EM)
15
Feb 26, 2026
18.4Joint Answer-Evidence Score
14
May 29, 2026
40.9Average Exact Match
14
May 14, 2026
45.5Accuracy (EM)
14
May 14, 2026
61.96EM
13
Feb 26, 2026
38.6EM
13
Feb 26, 2026