The MATH dataset benchmarks AI mathematical problem solving with 12,500 hard competition problems and reveals that scaling model size and data is insufficient for high performance.
The square of what other number is 225?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2021 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Measuring Mathematical Problem Solving With the MATH Dataset
The MATH dataset benchmarks AI mathematical problem solving with 12,500 hard competition problems and reveals that scaling model size and data is insufficient for high performance.