Generative Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
81.6GenQA Average
39
Apr 7, 2026
40.7ROUGE Score
18
Feb 26, 2026
57.2ROUGE Score
11
Feb 26, 2026
92HALL Score
10
Jun 2, 2026
67.33HALL Score
10
Jun 2, 2026
52HALL Score
10
Jun 2, 2026
82.33HALL Score
10
Jun 2, 2026
50.33HALL Rate
10
Jun 2, 2026
3.758Content Score
10
Feb 26, 2026
72.84Exact Match (EM)
8
Jun 11, 2026
57.99EM
8
Feb 26, 2026
61.19EM
8
Feb 26, 2026
43.01EM
8
Feb 26, 2026
76.42EM
8
Feb 26, 2026
73.34EM
8
Feb 26, 2026
67Accuracy
7
Mar 10, 2026
69.52EM
5
Jun 11, 2026
69.04EM
5
Jun 11, 2026
53.09BLEU-4
5
Feb 26, 2026
64.5ROUGE-1
4
May 29, 2026
51.7EM
3
Jun 11, 2026
54.1Exact Match (EM)
3
Jun 11, 2026
57.63EM
3
Feb 26, 2026