Download 164k Txt Apr 2026

If you are building a custom AI, you run it against these 164 problems to see its "Pass@k" score (the probability that at least one of the generated code samples passes the unit tests).

The name and parameters of the code to be written. Docstrings: A text description of what the code should do. Download 164K txt

This dataset is a benchmark created by OpenAI to test "code generation" capabilities. It consists of 164 Python programming tasks that include: If you are building a custom AI, you

You can find the official version through major AI research repositories: Download 164K txt