iiRecord
Agentic AI Atlas · RepoBench
benchmark:repobencha5c.ai
II.
Benchmark overview

benchmark:repobench

Reference · live

RepoBench overview

RepoBench evaluates repository-level code auto-completion across Python and Java. Sub-tasks measure retrieval, prediction, and end-to-end completion in real-world multi-file repositories.

BenchmarkOutgoing · 1Incoming · 1

Attributes

displayName
RepoBench
homepageUrl
kind
code-completion
targetsKind
ModelVersion
description
RepoBench evaluates repository-level code auto-completion across Python and Java. Sub-tasks measure retrieval, prediction, and end-to-end completion in real-world multi-file repositories.

Outgoing edges

applies_to1

Incoming edges

bounds_subject1