List your company

ResearchFormerly WizWand

Reward Modeling Suitability Evaluation

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

SOLAR-10.7B-Instruct-v1.0

-0.077EF

26

Feb 26, 2026

RM Bench Safety-accept

ArmoRM-Llama3-8B-v0.1

0.698EF

26

Feb 26, 2026