List your company
ResearchFormerly WizWand

LLM-as-a-Judge Evaluation on JudgeBench (test)

83.4ScoreSkywork-Reward-V2-Llama-3.1-8B-40M
40.34451.52262.773.878Jul 2, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Skywork-Reward-V2-Llama-3.1-8B-40M2025.0783.4
Skywork-Reward-V2-Llama-3.1-8B2025.0780
Skywork-Reward-V2-Qwen3-8B2025.0773.4
Skywork-Reward-V2-Qwen3-1.7B2025.0772.9
INF-ORM-Llama3.1-70BModel Type=Open Reward Model2025.0770.2
Skywork-Reward-V2-Qwen3-4B2025.0769.5
Skywork-Reward-V2-Llama-3.2-3B2025.0769.2
Skywork-Reward-V2-Qwen3-0.6B2025.0767.6
Skywork-Reward-Gemma-2-27B-v0.2Model Type=Open Reward Model2025.0766.5
Llama-3.1-Nemotron-70BModel Type=Open Reward Model2025.0765.8
Skywork-Reward-V2-Llama-3.2-1B2025.0765
Claude-3.5-SonnetModel Type=LLM-as-a-Judge2025.0764.8
Internlm2-20b-rewardModel Type=Open Reward Model2025.0764.3
LDL-Reward-Gemma-2-27B-v0.1Model Type=Open Reward Model2025.0764.2
Llama-3-OffsetBias-RM-8BModel Type=Open Reward Model2025.0763.5
Skywork-Reward-Llama-3.1-8B-v0.2Model Type=Open Reward Model2025.0762.9
J1-Llama-70BModel Type=LLM-as-a-Judge2025.0760
GPT-4oModel Type=LLM-as-a-Judge2025.0759.8
ArmoRM-Llama3-8B-v0.1Model Type=Open Reward Model2025.0759.7
EvalPlanner (Llama-3.3-70B)Model Type=LLM-as-a-Judge2025.0756.6
EvalPlanner (Llama-3.1-70B)Model Type=LLM-as-a-Judge2025.0750.9
J1-Llama-8BModel Type=LLM-as-a-Judge2025.0742