Definition
Plain language
A standard benchmark of Python programming problems.
As stated in the literature
MBPP, a crowd-sourced benchmark of Python coding tasks with reference solutions and unit tests.
Also called: MBPP
Why it matters: It's a low-barrier coding benchmark used as an early-stage check before harder evaluations like HumanEval or SWE-bench.
For example, a task might ask the model to write a function that returns the sum of the digits of an integer, checked by unit tests.