List your company

Reading Comprehension on Belebele Basque

94.22AccuracyClaude 3.5 Sonnet
73.076878.565984.05589.5441Jun 9, 2025

Evaluation results

MethodLinks
Claude 3.5 SonnetModel Scale=Proprietary2025.0694.22
GPT-4oModel Scale=Proprietary2025.0692.88
70B + CEU IENModel Scale=70B, Training Variant=+ CEU IEN2025.0691
70B INSTRUCT ENModel Scale=70B, Training Variant=INSTRUCT EN2025.0689.11
8B + CEU IEN+EUModel Scale=8B, Training Variant=+ CEU IEN+EU2025.0683
8B + CEU IEUModel Scale=8B, Training Variant=+ CEU IEU2025.0681.44
8B + CEU IENModel Scale=8B, Training Variant=+ CEU IEN2025.0680
8B INSTRUCT ENModel Scale=8B, Training Variant=INSTRUCT EN2025.0673.89