Home BIG-Bench
Post
Cancel

BIG-Bench

  • 🗂️Benchmark Name: PandasEval
  • 📚Publisher: arxiv
  • 🏠Author Affiliation: Google Research
  • 🔗URL: https://github.com/google/BIG-bench/tree/main/bigbench/benchmark_tasks/python_programming_challenge
  • Number of Instances: 32
  • Problem Description’s Natural Language: English
  • Code Solution’s Programming Language: Python
  • Data Statistics
    • Test Case: ✅
    • Average Number of Test Cases: 4.7
    • Average Number of Characters in Problem Description: 341.8
    • Average Number of Lines in Problem Description: 3.0
    • Average Number of Characters in Code Solution: /
    • Average Number of Lines in Code Solution: /
  • Scenario: Code Exercise
This post is licensed under CC BY 4.0 by the author.

GPT-NeoX

GSM8K-Python