Share your thoughts, 1 month free Claude Pro on usSee more

Reward Modeling on PPE Correlation

87.2Correlation

Skywork-Reward-V2-Llama-3.1-8B-40M

Updated 1mo ago

Evaluation Results

Method	Links
Skywork-Reward-V2-Llama-3.1-8B-40M 2025.07		87.2
Skywork-Reward-V2-Llama-3.1-8B 2025.07		83.4
Skywork-Reward-V2-Qwen3-8B 2025.07		75.1
Skywork-Reward-V2-Qwen3-4B 2025.07		74.7
J1-Llama-70B 2025.07		73.7
J1-Llama-70B 2025.07		72.9
Skywork-Reward-V2-Llama-3.2-3B 2025.07		72.1
Skywork-Reward-V2-Qwen3-1.7B 2025.07		70.5
Claude-3.5-Sonnet 2025.07		69.2
Skywork-Reward-V2-Qwen3-0.6B 2025.07		68.3
Skywork-Reward-V2-Llama-3.2-1B 2025.07		67.4
GPT-4o 2025.07		67.1
INF-ORM-Llama3.1-70B 2025.07		64.4
Llama-3-OffsetBias-RM-8B 2025.07		64.1
LDL-Reward-Gemma-2-27B-v0.1 2025.07		63.9
Llama-3.1-Nemotron-70B 2025.07		63.2
DeepSeek-GRM-27B 2025.07		63.2
Internlm2-20b-reward 2025.07		63
GRM-llama3-8B-distill 2025.07		62.8
Skywork-Reward-Llama-3.1-8B-v0.2 2025.07		62.5
Skywork-Reward-Gemma-2-27B-v0.2 2025.07		61.9
J1-Llama-8B 2025.07		61.9
FsfairX-LLaMA3-RM-v0.1 2025.07		61.1
ArmoRM-Llama3-8B-v0.1 2025.07		60.6
Eurus-RM-7b 2025.07		60.5
QRM-Llama3.1-8B 2025.07		60.5
URM-LLaMa-3.1-8B 2025.07		60.4
DeepSeek-GRM-27B 2025.07		60.4
QRM-Llama3.1-8B-v2 2025.07		60.3
Skywork-Reward-Llama-3.1-8B 2025.07		60.3
Skywork-Reward-Gemma-2-27B 2025.07		60.1
Internlm2-7b-reward 2025.07		60
GRM-Llama3-8B-rewardmodel-ft 2025.07		60
J1-Llama-8B 2025.07		59.2
GRM-gemma2-2B-rewardmodel-ft 2025.07		58.5
BTRM Qwen2 7b 0613 2025.07		58.4
Starling-RM-34B 2025.07		57.5
RM-Mistral-7B 2025.07		56.4
QRM-Gemma-2-27B 2025.07		54.8
internlm2-1.8b-reward 2025.07		53.6