MBPP

MBPP is a benchmark for code generation and code reasoning. The official description says: "Mostly Basic Python Problems - Python coding tasks". Below we describe in simple words what benchmarks of this type generally examine.

MBPP measures code generation and code reasoning. In detail, it checks:

• writing programs that must pass hidden unit tests
• predicting what a given piece of code outputs (true code comprehension)
• handling edge cases, not just the happy path
• producing runnable, correct solutions from short specifications

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: Mostly Basic Python Problems - Python coding tasks. 3-shot.

What is the MBPP benchmark?

MBPP is a benchmark for code generation and code reasoning. The official description says: 'Mostly Basic Python Problems - Python coding tasks'. Below we describe in simple words what benchmarks of this type generally examine.

What does MBPP test?

MBPP mainly measures code generation and code reasoning. Concretely, it checks: writing programs that must pass hidden unit tests; predicting what a given piece of code outputs (true code comprehension); handling edge cases, not just the happy path.

How is the MBPP score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get MBPP data and scores?

The official source is https://arxiv.org/abs/2108.07732. The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/mbpp/scores) or pull it directly from the Open LLM Radar API with any HTTP client.