cd /news/ai-research/embeddings-vs-grep-rethinking-the-de… · home › topics › ai-research › article
[ARTICLE · art-173096] src=aiflash.com ↗ pub= topic=ai-research verified=true sentiment=· neutral

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.

recommendation

Benchmark code retrieval on realistic repository-level queries with a properly tuned BM25 baseline before adopting dense embeddings; curated-query benchmarks overstate the dense advantage.

more in playbook: Evals and testing for LLM apps
read1 min views1 publishedNov 20, 2026

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

── more in #ai-research 4 stories · sorted by recency
── more on @repo-premium 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/embeddings-vs-grep-r…] indexed:0 read:1min 2026-11-20 · —