LLM Preference Alignment Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
55Preference (spec vs ctl)
1
Jun 24, 2026
84Preference Score (spec vs ctl)
1
Jun 24, 2026
73Preference Score (spec vs ctl)
1
Jun 24, 2026
78Preference Rate (spec vs ctl)
1
Jun 24, 2026
64Spec vs ctl Preference Score
1
Jun 24, 2026
71Preference Score (spec vs ctl)
1
Jun 24, 2026
66Preference Score (spec vs ctl)
1
Jun 24, 2026