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

Mathematical Reasoning on MathBench Middle

84.67Accuracy

Vanilla CoT

31.276445.13825972.8618Dec 24, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.12
84.67553.9368.22
2024.12
79.33238.1442.95
2024.12
33.3353.58