List your company

Helpfulness on HH-RLHF

8.75Gemini ScoreGGRO
6.81567.31787.828.3222Jun 8, 2026

Evaluation results

MethodLinks
GGROModel=LLaMA-3.1-8B-Instruct + Skywork-Reward-V2-LLaMA-3.1-8B2026.068.75
BoN (N=64)Model=LLaMA-3.1-8B-Instruct + Skywork-Reward-V2-LLaMA-3.1-8B2026.068.67
RSModel=LLaMA-3.1-8B-Instruct + Skywork-Reward-V2-LLaMA-3.1-8B2026.068.57
CARDSModel=LLaMA-3.1-8B-Instruct + Skywork-Reward-V2-LLaMA-3.1-8B2026.068.41
CBSModel=LLaMA-3.1-8B-Instruct + Skywork-Reward-V2-LLaMA-3.1-8B2026.068.39
RSModel=LLaMA-3.2-3B-Instruct + GRM-LLaMA-3.2-3B-rewardmodel-ft2026.068.13
ARGS-GModel=LLaMA-3.1-8B-Instruct + Skywork-Reward-V2-LLaMA-3.1-8B2026.068.12
BoN (N=64)Model=LLaMA-3.2-3B-Instruct + GRM-LLaMA-3.2-3B-rewardmodel-ft2026.068.11
GGROModel=LLaMA-3.2-3B-Instruct + GRM-LLaMA-3.2-3B-rewardmodel-ft2026.068.11
ARGS-GModel=LLaMA-3.2-3B-Instruct + GRM-LLaMA-3.2-3B-rewardmodel-ft2026.068.09
Vanilla LLMModel=LLaMA-3.1-8B-Instruct + Skywork-Reward-V2-LLaMA-3.1-8B2026.068.03
CBSModel=LLaMA-3.2-3B-Instruct + GRM-LLaMA-3.2-3B-rewardmodel-ft2026.067.91
CARDSModel=LLaMA-3.2-3B-Instruct + GRM-LLaMA-3.2-3B-rewardmodel-ft2026.067.71
Vanilla LLMModel=LLaMA-3.2-3B-Instruct + GRM-LLaMA-3.2-3B-rewardmodel-ft2026.067.66
SEAModel=LLaMA-3.1-8B-Instruct + Skywork-Reward-V2-LLaMA-3.1-8B2026.067.34
SEAModel=LLaMA-3.2-3B-Instruct + GRM-LLaMA-3.2-3B-rewardmodel-ft2026.066.89