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

Preference Evaluation on RMB Best-of-N

86.2Helpfulness Score (BoN)

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		86.2	86.6	86.4
Skywork-Reward-V2-Llama-3.1-8B 2025.07		82.3	82.8	82.5
Skywork-Reward-V2-Qwen3-8B 2025.07		76.5	75.8	76.2
Skywork-Reward-V2-Qwen3-4B 2025.07		74.7	75.1	74.9
Skywork-Reward-V2-Llama-3.2-3B 2025.07		74.4	76.2	75.3
Skywork-Reward-V2-Qwen3-1.7B 2025.07		72	72.2	72.1
Skywork-Reward-V2-Qwen3-0.6B 2025.07		68.4	69.1	68.8
Skywork-Reward-V2-Llama-3.2-1B 2025.07		68	73.2	70.6
Qwen2-72B-Instruct 2025.07		64.5	64.9	64.7
DeepSeek-GRM-27B + MetaRM 2025.07		64.2	58	61.1
DeepSeek-GRM-27B 2025.07		63.9	58	61
GPT-4o-2024-05-03 2025.07		63.9	68.2	66.1
RM-R1-Qwen-Instruct-32B 2025.07		63.6	68.2	65.9
Skywork-Reward-Gemma-2-27B-v0.2 2025.07		63.1	59.9	61.5
RM-R1-DeepSeek-Distill-Qwen-32B 2025.07		62	61.8	61.9
Skywork-Reward-Llama-3.1-8B-v0.2 2025.07		60.5	56.8	58.7