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

Arithmetic Reasoning on AddSub (test)

96.71Accuracy

CoT + Skill-Based

88.015690.272892.5394.7872Jun 6, 2023Aug 3, 2023Sep 30, 2023Nov 27, 2023Jan 24, 2024Mar 22, 2024May 20, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.05
96.71
2024.05
95.7
2024.05
94.9
2024.05
93.9
2023.06
93.67
2023.06
93.54
2023.06
92.36
2023.06
88.35