List your company

Pairwise Ranking on Seven Harm Categories

83.1Insult Pairwise ScoreOAI-RM
-0.72421.03842.864.562Mar 23, 2025

Evaluation results

MethodLinks
OAI-RMBase Model=Llama-3.1-8B2025.0383.181.979.780.582.378.980.1
Shadow-RMBase Model=Llama-3.1-8B2025.039.39.910.510.49.410.710.7
Anthropic-RMBase Model=Llama-3.1-8B2025.032.52.32.42.92.43.13.7