Benchmark

SAGE: Science Answer Grading & Evaluation

Compare models to automatically grade written responses to science questions

Tasks
Grading science/math
Grading writing
Data types
Tabular
Eleni Koureas on Unsplash, generated using Gemini

Community Code

This is where users can share their work to help and inspire others. Posts can range from short snippets to longer guides covering tips for getting started, interesting analyses or visualizations, modeling approaches, or something else!

You will have the option to edit your post after submitting.

Tips

The best posts will be easy to follow and any code will be well documented. Some tips for creating a good post:

  • Include a short introduction summarizing what the post contains.
  • Do not print out full dataframes or other full data structures, unless they are very small. Long outputs make the narrative harder to follow. Instead, print out data samples and summary statistics.
    • For example, if you are working with a pandas DataFrame print out df.head() or df.sample(n=5) rather than df. Similarly, use df.describe() to see summary statistics.
  • Do not print out extremely long log outputs. Pro tip: you can suppress the output of a Jupyter notebook cell by adding %%capture to the top.
  • Break the post up into explanatory sections, such as "Intro", "Load the data", "Process the data", "Exploratory Data Analysis", and "Visualization". If you are working in a Jupyter notebook, use Markdown cells to add narrative and headers for different sections.
  • Document your code. Explain what different parts do with comments, docstrings, or text blocks.

Posts (0)

No posts found. Why not contribute a post of your own?