Open-domain QA
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
64.7F1 Score
33
Apr 27, 2026
62.3Average EM
30
May 13, 2026
74.4EM
20
Mar 19, 2026
37.6QA-F1
16
Feb 26, 2026
47QA-F1
16
Feb 26, 2026
41.8QA-F1
16
Feb 26, 2026
48.1QA-F1
16
Feb 26, 2026
0.311Exact Match
10
Feb 26, 2026
64.5EM
10
Feb 26, 2026
38.6F1
10
Feb 26, 2026
52.3EM
10
Feb 26, 2026
40.3Exact Match
10
Feb 26, 2026
78.2Accuracy
8
Feb 26, 2026
20.75R-L
8
Feb 26, 2026
72.94EM
8
Feb 26, 2026
44.6Accuracy
6
Feb 26, 2026
0.473Acc
6
Feb 26, 2026
78.76AVG Score
4
Feb 26, 2026