Agentic AI Atlasby a5c.ai
/
GitHubDocsDiscord
iiRecord
Agentic AI Atlas · HumanEval original problem set
test-set:humaneval-originala5c.ai
II.
TestSet overview

test-set:humaneval-original

Reference · live

HumanEval original problem set overview

Canonical HumanEval artifact for Python code-generation evaluation.

TestSetOutgoing · 1Incoming · 0

Attributes

displayName
HumanEval original problem set
benchmarkId
benchmark:human-eval
caseCount
164
releasedAt
2021-07-07
composition
Hand-written Python function-completion problems for evaluating functional correctness of generated code from signatures and docstrings.
homepageUrl
https://github.com/openai/human-eval
description
Canonical HumanEval artifact for Python code-generation evaluation.

Outgoing edges

belongs_to_benchmark1

Incoming edges

None.