MultiPL-HumanEval

• 🗂️Benchmark Name: MultiPL-HumanEval
• 📚Publisher: Arxiv
• 🔗URL: https://github.com/nuprl/MultiPL-E/tree/main/datasets
• Number of Instances: 164 per programming language
• Problem Description’s Natural Language: English
• Code Solution’s Programming Language: Python, Bash, C++, C#, D, Go, Java, JavaScrpt, Julia, Lua, Perl, PHP, R, Racket, Ruby, Rust, Scala, Swift, TypeScript
• Data Statistics
  • Test Case: ✅
  • Average Number of Test Cases: 7.8
  • Average Number of Characters in Problem Description: 453.9
  • Average Number of Lines in Problem Description: 13.0
  • Average Number of Characters in Code Solution: /
  • Average Number of Lines in Code Solution: /
• Scenario: Multilingual