Personalized Response Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
4.032RSA
13
Feb 26, 2026
83.91Win Rate
12
Feb 26, 2026
79.1Preference Score
8
Jun 2, 2026
0.474Pref Score
8
Jun 2, 2026
69.9Pref
8
Jun 2, 2026
0.221Preference Score
8
Jun 2, 2026
84.6Winrate
8
Apr 20, 2026
92.3Winrate
8
Apr 20, 2026
73.4Macro Accuracy
4
Feb 26, 2026
24Macro Accuracy
4
Feb 26, 2026