Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.03MMD
7
Mar 12, 2026
0.01MMD
7
Mar 12, 2026
9.7FID
6
Jun 9, 2026
80.4SQuAD Score
6
May 4, 2026
0.837Accuracy
6
Mar 24, 2026
0.58Cite Score
6
Feb 26, 2026
82Success@1Å
5
Jun 29, 2026
70.5Pass@95
5
Jun 29, 2026
90.6Pass@95
5
Jun 29, 2026
100Solve Rate
5
Jun 29, 2026
100Avoidance
5
Jun 29, 2026
1.27Mean 1-Wasserstein Distance
5
Jun 16, 2026
4.93Mean 1-Wasserstein Distance
5
Jun 16, 2026
90.2Urdu Generation Score
5
Feb 26, 2026
69.5Execution Accuracy
4
Jun 18, 2026
71.3Execution Accuracy
4
Jun 18, 2026
50.7Execution Accuracy
4
Jun 18, 2026
77.8Execution Accuracy
4
Jun 18, 2026
59Exact Match
4
Apr 14, 2026
81.5Truthfulness x Informativeness Score
4
Apr 14, 2026
55.39Top-1 Accuracy
4
Mar 6, 2026
48.02Top-1 Accuracy
4
Mar 6, 2026
58.22Top-1 Accuracy
4
Mar 6, 2026
0.789CLIP-I
3
Mar 16, 2026
87.6ROUGE-1
3
Feb 26, 2026