II.
TestSet overview
Reference · livetest-set:bigcodebench-full
BigCodeBench full set overview
Canonical full-set artifact for BigCodeBench code-generation evaluation.
Attributes
displayName
BigCodeBench full set
benchmarkId
caseCount
1140
releasedAt
2024-06-17
composition
Full BigCodeBench practical Python code-generation set covering
diverse function calls across 139 libraries and seven domains.
homepageUrl
description
Canonical full-set artifact for BigCodeBench code-generation evaluation.
Outgoing edges
belongs_to_benchmark1
- benchmark:bigcodebench·BenchmarkBigCodeBench
Incoming edges
None.