Benchmark Radar™
Star —

RepoMirage Benchmark

Explore score history ↗

RepoMirage is a two-stage evaluation suite built on SWE-Bench Verified that applies semantics-preserving repository-level perturbations and extended tasks to probe repository context reasoning in code agents.

Released
2026-05-25
Institutions
Beijing University of Posts and Telecommunications · Tsinghua University · Tencent (China)
Evaluates
Code & Software, Reasoning, Software & AI Compute
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

RepoMirage paper

No reported scores are on record for this benchmark yet.

Which sources cite RepoMirage?

Related Code & Software, Reasoning, Software & AI Compute benchmarks