Skip to content

Dataset / Data Pipeline

arc-prompt

Prompts for solving ARC (Abstraction and Reasoning Corpus) with GPT4 or similar

What it is

The repository is a collection of prompt-engineering examples (prompts and LLM responses) for solving ARC tasks with large language models. It documents which prompts yield correct or incorrect predictions and includes informal learnings about prompt design.

  • arc-agi
  • llm
  • prompt
  • prompt-engineering
  • prompts
Scored at885669314 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Distribution based on AI work

1 / 2
NLP & LLMs: 72.7%Data Science: 18.2%Computer Vision: 9.1%
  • NLP & LLMs73%
  • Data Science18%
  • Computer Vision9%

Each field's share of the project's AI work, as scoring counts it. It ranks in the field it is most about.

What the judge found

Read from the project's code at its scored commit.

Strengths2

  • Extensive collection of prompt-engineering examples for ARC tasks.
  • Documentation of informal learnings about prompt design in the README.

Limitations

The owner keeps this project's limitations private.

Around it on the NLP & LLMs board

Whole board
  1. 196oya-agent-google-my-business-reviews-responderTutorial / Demo · Python24.9/100ExplorationYazeed Al Oyoun
  2. 197deep-searchEducational Implementation · TypeScript24.3/100ExplorationPetr Sovadina
  3. 198arc-promptDataset / Data Pipeline24.0/100ExplorationSimon Strandgaard
  4. 199totumchatTutorial / Demo · HTML23.0/100Explorationjerry howell
  5. 200langfuseTutorial / Demo · Jupyter Notebook22.6/100ExplorationPetr Sovadina

More from Simon Strandgaard