Measuring Coding Challenge Competence With APPSDownload PDF

Published: 11 Oct 2021, Last Modified: 01 Oct 2023NeurIPS 2021 Datasets and Benchmarks Track (Round 2)Readers: Everyone
Keywords: code, programming, transformers, program synthesis
TL;DR: Can Transformers crack the coding interview? We collected 10,000 programming problems to find out. GPT-3 does not perform well, but new models like GPT-Neo are starting to be able to solve introductory coding challenges.
Abstract: While programming is one of the most broadly applicable skills in modern society, it is unclear how well state-of-the-art machine learning models can write code. Despite its importance, there has been surprisingly little work on evaluating code generation, and it can be difficult to assess code generation performance in an accurate and rigorous manner. To meet this challenge, we introduce APPS, a benchmark for code generation. Unlike prior work in more restricted settings, our benchmark measures the ability of models to take an arbitrary natural language specification and generate satisfactory Python code. Similar to how companies assess candidate software developers, we evaluate models by checking their generated code on test cases. Our benchmark includes 10,000 problems, which range from having simple one-line solutions to being substantial algorithmic challenges. We fine-tune large language models on both GitHub and our training set, and we find that the prevalence of syntax errors is decreasing exponentially as models improve. Recent models such as GPT-Neo can pass approximately 20% of the test cases of introductory problems, so we find that machine learning models are now beginning to learn how to code. As the social significance of automatic code generation increases over the coming years, our benchmark can provide an objective measure for tracking advancements.
Supplementary Material: zip
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](
16 Replies