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

Human Preference Evaluation on Basque Arena

1,183Arena Content Score

GPT-4o

749.32861.91974.51,087.09Jun 9, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.06
1,1831,0931,188
2025.06
1,1501,0821,153
2025.06
1,1271,0831,141
2025.06
1,0471,0381,050
2025.06
1,0451,0341,050
2025.06
1,0311,0361,038
2025.06
766783722