List your company
ResearchFormerly WizWand

Reward Modeling on WPB

63.89AccuracyR1-Distill-Qwen-32B
44.192449.306254.4259.5338Jan 12, 2026
Updated 8mo ago

Evaluation results

MethodLinks
R1-Distill-Qwen-32BModel Category=Base Models (LLM-as-a-Judge), Backbone=Qwen-32B2026.0163.89
gemini-2.5-proModel Category=Base Models (LLM-as-a-Judge)2026.0163.67
RM-R1-Qwen-32BModel Category=Specialized Generative Reward Models, Backbone=Qwen-32B2026.0163.67
RRM-Qwen-32BModel Category=Specialized Generative Reward Models, Backbone=Qwen-32B2026.0162.83
qwen-plus-latestModel Category=Base Models (LLM-as-a-Judge)2026.0162.78
o3-2025-04-16Model Category=Base Models (LLM-as-a-Judge)2026.0162.34
deepseek-r1-0528Model Category=Base Models (LLM-as-a-Judge)2026.0161.83
RM-NLHF-Qwen-32BModel Category=Our Generative Reward Models, Backbone=Qwen-32B2026.0161.83
qwen3-maxModel Category=Base Models (LLM-as-a-Judge)2026.0161.33
deepseek-v3Model Category=Base Models (LLM-as-a-Judge)2026.0161.22
claude-3-7-sonnet-20250219Model Category=Base Models (LLM-as-a-Judge)2026.0159.67
INF-ORM-Llama3.1-70BModel Category=Scalar Reward Models, Backbone=Llama-3.1-70B2026.0159.67
gpt-5-2025-08-07Model Category=Base Models (LLM-as-a-Judge)2026.0159.39
gpt-4o-latestModel Category=Base Models (LLM-as-a-Judge)2026.0158.83
R1-Distill-Llama-8BModel Category=Base Models (LLM-as-a-Judge), Backbone=Llama-8B2026.0158.41
RM-NLHF-Qwen-7BModel Category=Our Generative Reward Models, Backbone=Qwen-7B2026.0155.21
Skywork-Reward-Llama-3.1-8B-v0.2Model Category=Scalar Reward Models, Backbone=Llama-3.1-8B2026.0153.22
RM-R1-Qwen-7BModel Category=Specialized Generative Reward Models, Backbone=Qwen-7B2026.0152.61
DeepSeek-R1-Distill-Qwen-7BModel Category=Base Models (LLM-as-a-Judge), Backbone=Qwen-7B2026.0151.61
RRM-Qwen-7BModel Category=Specialized Generative Reward Models, Backbone=Qwen-7B2026.0151.61
URM-LLaMa-3.1-8BModel Category=Scalar Reward Models, Backbone=Llama-3.1-8B2026.0148.84
ArmoRM-Llama3-8B-v0.1Model Category=Scalar Reward Models, Backbone=Llama3-8B2026.0144.95