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

LLM Evaluation on JudgeBench (test)

79.9Knowledge

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

49.42857.33965.2573.161Jul 2, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.07
79.978.689.385.783.4
2025.07
76.675.589.378.680
2025.07
70.167.382.173.873.3
2025.07
67.589.887.510086.2
2025.07
66.969.483.971.472.9
2025.07
66.964.380.466.769.5
2025.07
66.279.685.785.779.3
2025.07
64.365.387.559.569.2
2025.07
6369.483.483.374.8
62.366.366.164.364.8
2025.07
62.386.785.792.981.9
2025.07
62.366.382.159.567.5
2025.07
6166.373.259.565
59.182.780.492.978.8
2025.07
58.462.282.178.670.3
2025.07
50.654.17559.559.8