Personalization
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
82.71Accuracy
80
Mar 4, 2026
94.84Win Rate
45
Mar 23, 2026
81.62Personalization Win Rate
45
Mar 23, 2026
93.67Personalization Win-Rate
45
Mar 23, 2026
0.998Creative Score (ArmoRM)
33
Jun 2, 2026
67.9Acc
22
Mar 4, 2026
0.241MAE
21
May 29, 2026
0.844CLIP-I Score
19
Jul 2, 2026
57Creative ArmoRM Score
18
Jun 2, 2026
56Creative Score (ArmoRM)
18
Jun 2, 2026
0.51Creative ArmoRM Score
18
Jun 2, 2026
85.2Accuracy
14
Mar 4, 2026
49.2ROUGE-1
14
Mar 4, 2026
0.739DINO Score
11
Mar 24, 2026
0.739DINO Score
11
Mar 24, 2026
7.2Personalization Score
10
Feb 26, 2026
21.2ROUGE-1
8
Feb 26, 2026
65.6Accuracy
8
Feb 26, 2026
7.35Score
6
Feb 26, 2026
67.5Wealth-Seeking Score
6
Feb 26, 2026
0.445Power-Seeking
6
Feb 26, 2026
0.73CP
5
Feb 26, 2026
0.7CP
5
Feb 26, 2026
38.33Accuracy
4
Jul 3, 2026
91.8Winrate
4
Apr 20, 2026