Open-domain Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
35.9EM & F1 Score
6
Feb 26, 2026
73.4F1 Score
6
Feb 26, 2026
71EM & F1 Score
6
Feb 26, 2026
68.3F1 Score
6
Feb 26, 2026
45.7F1 Score
6
Feb 26, 2026
43.9F1 Score
6
Feb 26, 2026
41.9EM & F1 Score
6
Feb 26, 2026
40.6EM/F1 Score
6
Feb 26, 2026
37.8EM & F1
6
Feb 26, 2026
46.4EM/F1 Score
6
Feb 26, 2026
42.1F1 Score
6
Feb 26, 2026
38.5Exact Match / F1
6
Feb 26, 2026
77.3Exact Match (EM)
6
Feb 26, 2026
47.7Accuracy
6
Feb 26, 2026
33Rouge-L
5
May 28, 2026
40.2EM
5
Feb 26, 2026
0.261EM
5
Feb 26, 2026
36.9F1 Score
5
Feb 26, 2026
52.51Trivia QA Score
5
Feb 26, 2026
21EM
5
Feb 26, 2026
16.1EM
5
Feb 26, 2026
53.1Accuracy
5
Feb 26, 2026
92Platinum Score
5
Feb 26, 2026
58.5Exact Match
5
Feb 26, 2026
45.42NOB Accuracy
5
Feb 26, 2026