List your company

Multiple Choice Question Answering on EusExams

82.68AccuracyClaude 3.5 Sonnet
44.751254.598164.44574.2919Jun 9, 2025

Evaluation results

MethodLinks
Claude 3.5 SonnetModel Scale=Proprietary2025.0682.68
GPT-4oModel Scale=Proprietary2025.0679.17
70B + CEU IENModel Scale=70B, Training Variant=+ CEU IEN2025.0671.56
70B INSTRUCT ENModel Scale=70B, Training Variant=INSTRUCT EN2025.0663.28
8B + CEU IEN+EUModel Scale=8B, Training Variant=+ CEU IEN+EU2025.0656.23
8B + CEU IEUModel Scale=8B, Training Variant=+ CEU IEU2025.0656.01
8B + CEU IENModel Scale=8B, Training Variant=+ CEU IEN2025.0656
8B INSTRUCT ENModel Scale=8B, Training Variant=INSTRUCT EN2025.0646.21