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

Arithmetic Reasoning on KVFundaBench AR

87.79Accuracy (Exact Match)

FullKV

47.656458.075768.49578.9143Feb 4, 2025
Updated 2mo ago

Evaluation Results

MethodLinks
2025.02
87.79
2025.02
80.41
2025.02
73.78
2025.02
64.41
2025.02
49.2