Preference Estimation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
469.25Beta_A Estimate
10
Apr 20, 2026
467.07β̂A
10
Apr 20, 2026
453.64Beta Estimate A
10
Apr 20, 2026
421.27Beta Estimate A
10
Apr 20, 2026
56.91Average Outcome Reward
9
Mar 13, 2026
61.28Average Outcome Reward
9
Mar 13, 2026
80.33Average Outcome Reward
9
Mar 13, 2026
54.67Average Outcome Reward
9
Mar 13, 2026
112MSE (Mayor)
3
Apr 20, 2026