Question Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
25.8BLEU-4
29
Feb 26, 2026
47.11Win Rate
25
Feb 26, 2026
44.61BLEU-1
22
Feb 26, 2026
0.496BLEU-4
21
Feb 26, 2026
0.263METEOR
21
Feb 27, 2026
54.8ROUGE-L
17
Feb 26, 2026
25.4BLEU-4
16
Feb 26, 2026
20.44BLEU
14
Feb 26, 2026
0.186BLEU
13
May 21, 2026
99.5Unique Questions
12
Jun 18, 2026
60.8METEOR
12
Feb 26, 2026
27.33ROUGE-1
11
Feb 26, 2026
24.43BLEU-4
10
Feb 26, 2026
0.163BLEU
9
May 21, 2026
68.35Distinct-1
9
Feb 26, 2026
26.95BLEU-4
9
Feb 27, 2026
27.79BLEU-4
8
Jun 5, 2026
22.71BLEU
8
Feb 26, 2026
20.26BLEU Score
8
Feb 26, 2026
59.3F1 (BLEU-1)
7
Feb 26, 2026
65.5F1 (BLEU-1)
7
Feb 26, 2026
26.3BLEU-4
7
Feb 26, 2026
97.71Unique
6
Jun 18, 2026
29.03B4
6
Feb 26, 2026
0.656Q-B4
6
Feb 26, 2026