Embeddings vs. Grep: Rethinking the Dense Advantage in Code Search A new repository-level code-search benchmark, Repo-Premium, finds that the reported advantage of dense embedding encoders over BM25 may be overstated because existing benchmarks use curated queries, old code and a handicapped BM25, even as coding agents perform well with plain grep. The work questions what the dense advantage in code search actually measures. Code-search benchmarks show dense encoders well ahead of BM25, yet coding agents do well with grep. What does this dense advantage measure? Existing benchmarks cannot tell: they use curated queries, old code and a handicapped BM25. To find out, we build Repo-Premium, a realistic repository-level cod