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

Response Generation on UltraFeedback (val)

88.1BERTScore

RPO

78.42880.93983.4585.961Jun 16, 2025
Updated 1d ago

Evaluation Results

MethodLinks
2025.06
88.134.80.791108--
2025.06
8834.60.791107--
2025.06
87.934.40.790106--
2025.06
87.131.60.98684--
2025.06
8729.70.88891--
2025.06
86.932.61.1849488.986.5
2025.06
86.832.31.1849589.887.4
2025.06
86.7321.2839389.586.9
2025.06
86.628.91.28372--
2025.06
86.431.91.2829189.887.3
2025.06
86.331.51.2828990.788.2
2025.06
86.231.11.3818890.287.9
2025.06
86.131.21.3818888.686.2
2025.06
8630.91.3808689.487.1
2025.06
85.930.31.3797185.983.8
2025.06
85.830.51.4808589.186.8
2025.06
85.625.21.5766384.582.1
2025.06
85.4251.2787385.183
2025.06
85.124.41.6746686.284.1
2025.06
8523.71.3745983.180.8
2025.06
84.624.11.7736085.883.2
2025.06
84.222.81.8715481.479.2
2025.06
8424.92.475658784.6
2025.06
78.824.82.4705792.790.1