Story Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
100Win Rate
42
Mar 18, 2026
7Cultural Relevance
27
Feb 26, 2026
8.5Cultural Relevance
27
Feb 26, 2026
8.6Cultural Relevance
27
Feb 26, 2026
0.2MAE
24
Apr 8, 2026
0.21MAE
24
Apr 8, 2026
0.476Pearson's r
24
Feb 26, 2026
0.13MAE
20
Apr 8, 2026
0.26MAE
20
Apr 8, 2026
0.25MAE
20
Apr 8, 2026
8.36Diversity
19
May 12, 2026
98.44Brier Accuracy (BA)
16
May 12, 2026
89.45Creativity
12
Apr 8, 2026
74.6Fascination
12
Feb 26, 2026
8.9Coherence (CR)
9
Feb 26, 2026
8Cultural Relevance
9
Feb 26, 2026
7.8Coherence Rating (CR)
9
Feb 26, 2026
100BLEU
9
Feb 26, 2026
100BLEU Score
9
Feb 26, 2026
28.1BLEU-1
9
Feb 26, 2026
18Rouge-L
8
Feb 27, 2026
20.4Rouge-L
8
Feb 27, 2026
30.9BL
8
Feb 26, 2026
0.779Spearman ρ
7
Jun 2, 2026
89Story Count
6
Jul 2, 2026