Creative Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
165Votes
20
May 20, 2026
69.92Accuracy
9
Jun 30, 2026
56.94ACC
9
Jun 30, 2026
93.56Recall
9
Jun 30, 2026
78.52Recall (Rec)
9
Jun 30, 2026
27.88Pass@1
9
Mar 13, 2026
39.01Pass@1
9
Mar 13, 2026
0.135Novelty
8
Jun 29, 2026
94.81Recall
8
Jun 17, 2026
8.82VLM Judge Score
4
Mar 19, 2026
8.2VLM-as-a-Judge Score
3
Mar 19, 2026
8.44VLM Judge Score
3
Mar 19, 2026