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

Mathematical Problem Solving on Aggregated Math Benchmarks

49.4Average Accuracy

DART-Math-DSMath-7B

49.19249.24649.349.354Jun 18, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.06
49.4
2024.06
49.3
2024.06
49.2