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

Reward Modeling on RMB (test)

89.3Score

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		89.3
Skywork-Reward-V2-Llama-3.1-8B 2025.07		86.4
Skywork-Reward-V2-Qwen3-8B 2025.07		81.2
Skywork-Reward-V2-Qwen3-4B 2025.07		80.6
Skywork-Reward-V2-Llama-3.2-3B 2025.07		80.5
Skywork-Reward-V2-Qwen3-1.7B 2025.07		78.1
Skywork-Reward-V2-Llama-3.2-1B 2025.07		76.7
Skywork-Reward-V2-Qwen3-0.6B 2025.07		74.5
GPT-4o 2025.07		73.8
RM-R1-Qwen-Instruct-32B 2025.07		73
Claude-3.5-Sonnet 2025.07		70.6
INF-ORM-Llama3.1-70B 2025.07		70.5
DeepSeek-GRM-27B (w/ MetaRM) 2025.07		70.3
RM-R1-DeepSeek-Distill-Qwen-32B 2025.07		69.8
Skywork-Reward-Gemma-2-27B-v0.2 2025.07		69.4
DeepSeek-GRM-27B 2025.07		69
LDL-Reward-Gemma-2-27B-v0.1 2025.07		67.9
Skywork-Reward-Llama-3.1-8B-v0.2 2025.07		66.6
Llama-3.1-Nemotron-70B 2025.07		64.9
ArmoRM-Llama3-8B-v0.1 2025.07		64.6
Internlm2-20b-reward 2025.07		62.9
Llama-3-OffsetBias-RM-8B 2025.07		57.8