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

General Knowledge Evaluation on C-Eval (val)

34.32Accuracy

LLaMA2-13B

22.422425.511228.631.6888Jul 23, 2024Nov 6, 2024Feb 20, 2025Jun 7, 2025Sep 21, 2025Jan 5, 2026Apr 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2024.07
34.32
2024.07
27.86
2024.07
27.49
2024.07
27.12
2024.07
26.79
2024.07
26.74
2024.07
26.37
2026.04
26.15
2026.04
25.56
2026.04
24.89
2026.04
24.67
2026.04
24.44
2024.07
23.92
2026.04
23.7
2026.04
22.88