APPS benchmark shows models like GPT-Neo pass roughly 20% of test cases on introductory problems, indicating machine learning is beginning to learn basic coding.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2021 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Measuring Coding Challenge Competence With APPS
APPS benchmark shows models like GPT-Neo pass roughly 20% of test cases on introductory problems, indicating machine learning is beginning to learn basic coding.