Measuring Coding Challenge Competence With APPS

By Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song and 1 more. 2021

1,191 citations recorded by the source corpus.

While programming is one of the most broadly applicable skills in modern society, modern machine learning models still cannot code solutions to basic problems. Despite its importance, there has been surprisingly little work on evaluating code generation, and it can be difficult to accurately assess code generation performance rigorously. 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 then 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 important measure for tracking advancements.

Subfields: Artificial Intelligence, Information Systems, Software, Evaluation & Benchmarks, Code Generation & Program Synthesis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Percy Liang
  3. Jianfeng Gao
  4. Luke S. Zettlemoyer
  5. Yoshua Bengio
  6. Quoc V. Le
  7. Graham Neubig
  8. Sergey Levine

In Information Systems

  1. Percy Liang
  2. Graham Neubig
  3. Charles Sutton
  4. Xinyun Chen
  5. Chun Xia
  6. Lingming Zhang
  7. Koushik Sen
  8. Luke S. Zettlemoyer

In Software

  1. Josh Tenenbaum
  2. Chun Xia
  3. Lingming Zhang
  4. Koushik Sen
  5. Pushmeet Kohli
  6. Percy Liang
  7. Armando Solar-Lezama
  8. Michihiro Yasunaga

In Evaluation & Benchmarks

  1. Ashish Sabharwal
  2. Chitta Baral
  3. Luke S. Zettlemoyer
  4. Peter Clark
  5. Mohit Bansal
  6. Percy Liang
  7. Pieter Abbeel
  8. Dan Roth

In Code Generation & Program Synthesis

  1. Charles Sutton
  2. Graham Neubig
  3. Augustus Odena
  4. Baptiste Rozière
  5. Guillaume Lample
  6. Josh Tenenbaum
  7. Chun Xia
  8. Lingming Zhang

Citations in the corpus