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

Mathematical Reasoning on MathBench High

84Accuracy

Vanilla CoT

50.023258.844167.66576.4859Dec 24, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.12
84653.2482.44
2024.12
80254.8247.61
2024.12
51.3354.07