Our new X account is live! Follow @wizwand_team for updates

Reward Modeling on RM-Bench Hard

0.697Accuracy

WILDREWARD-8B

Updated 4d ago

Evaluation Results

Method	Links
WILDREWARD-8B 2026.02		0.697
WILDREWARD-4B 2026.02		0.686
Internlm2-20b-reward 2026.02		0.628
Llama-3-OffsetBias-RM-8B 2026.02		0.569
ArmoRM-Llama3-8B-v0.1 2026.02		0.558
INF-ORM-Llama3.1-70B 2026.02		0.54
Athene-RM-8B 2026.02		0.514
Skywork-Reward-Llama-3.1-8B-v0.2 2026.02		0.493
Llama-3.1-Nemotron-70B 2026.02		0.478
Skywork-Reward-Gemma-2-27B-v0.2 2026.02		0.421