Glossary · Term

HumanEval

← all terms

Definition

Plain language

A small set of programming problems used as a standard test for code-generating models.

As stated in the literature

OpenAI's hand-written benchmark of Python programming problems with unit tests, used to measure functional code generation accuracy.

Why it matters: It became one of the default yardsticks for comparing code-generation models, shaping which systems get called 'good at programming.'

For example, a model might be asked to write a Python function that returns the longest common prefix of a list of strings, then graded on whether its code passes the hidden unit tests.

Heard on the show

“HumanEval problem one: split a string of nested parenthesis groups.”
Episode 233 — Why a Model Can Grade an Answer But Not Write the Answer Key

Mentioned in 3 episodes

  1. 233
    Why a Model Can Grade an Answer But Not Write the Answer Key
  2. 060
    When Splitting One Model Across Three Agents Doubles Its Accuracy
  3. 013
    Why Search Keeps Rediscovering the Same Workflow, and What That Means

Related terms