Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Offline Constrained RLHF research benchmarks · SOTA2 Research

Offline Constrained RLHF

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

PKU-SafeRLHF 74k (train)

-1.603Safety Expected Reward (r1)

2

Apr 2, 2026

PKU-SafeRLHF 7k (test)

-1.604Safety Reward (r1)

1

Apr 2, 2026

Popular datasets

Follow for updates

Join SOTA2 Contact