List your company

Human Preference Evaluation on Basque Arena

1,183Arena Content ScoreGPT-4o
749.32861.91974.51,087.09Jun 9, 2025

Evaluation results

MethodLinks
GPT-4oModel Scale=Proprietary2025.061,1831,0931,188
Claude 3.5 SonnetModel Scale=Proprietary2025.061,1501,0821,153
70B + CEU IENModel Scale=70B, Training Variant=+ CEU IEN2025.061,1271,0831,141
8B + CEU IEN+EUModel Scale=8B, Training Variant=+ CEU IEN+EU2025.061,0471,0381,050
8B + CEU IEUModel Scale=8B, Training Variant=+ CEU IEU2025.061,0451,0341,050
8B + CEU IENModel Scale=8B, Training Variant=+ CEU IEN2025.061,0311,0361,038
8B INSTRUCT ENModel Scale=8B, Training Variant=INSTRUCT EN2025.06766783722