← All comparisons
Atelier vs cocoindex-code
What cocoindex-code says, vs. what it scored.
AST-based semantic code search built on CocoIndex, a Rust data-transformation engine; tree-sitter parsing plus embeddings.
What cocoindex-code says about itself
“A lightweight, effective (AST-based) semantic code search tool for your codebase... Instant token saving by 70%.”
Publishes some numbers ...never against another search tool ~1.6k stars
What it actually scored — same 14 repos, same 7,213 queries as every other tool
| Tool | MRR | p95 | p100 |
|---|---|---|---|
| ★ Atelier +semantic (BGE) | 0.727 | 390ms | 1057ms |
| ★ Atelier lexical (default) | 0.676 | 134ms | 319ms |
| cocoindex-code | 0.557 | 595ms | 2061ms |
The 70% figure is real, but it's token count against reading whole files -- not against another code-search tool, and not an accuracy number. It's the closest challenger to Atelier here (0.557 MRR), but that's never been shown on a shared query set before this.
The true story
Every tool in this comparison, cocoindex-code included, has been through the exact same 14 repositories and 7,213 query/gold pairs that score Atelier — no cherry-picked queries, no separate corpus. Full methodology, every raw number, and the other 9 tools →