What they say vs. what it produces

Every comparison, with sources.

We ran Atelier and 10 named code-search tools through the identical 14-repo, 7,213-query benchmark -- same corpus, same query kinds, same scoring. 7 of 10 publish some number about themselves; 1 of 10 has ever benchmarked itself against another search tool on the same axis we measure here. None had been scored against each other before this page existed.

The flagship comparison

Atelier vs. vanilla Claude Code →

Every published suite: SWE-bench, Exploration, Terminal-Bench, Telegraphic Q&A

Same model. Same tasks. Same environment. Anthropic doesn't publish Claude Code's own cost/token/turn efficiency numbers against anything -- so this is the head-to-head Anthropic itself has never run.

Code-search retrieval tools, ranked by MRR
Atelier vs cocoindex-code 0.557 MRR

AST-based semantic code search built on CocoIndex, a Rust data-transformation engine; tree-sitter parsing plus embeddings.

Self-benchmarked, never vs. a rival →
Atelier vs codebase-memory-mcp 0.502 MRR

Tree-sitter-based persistent knowledge graph (SQLite-backed) across 158 languages -- the most-starred tool in this comparison.

Self-benchmarked, never vs. a rival →
Atelier vs fff (fff-mcp) 0.430 MRR

In-memory, frecency-ranked file and content search with a background watcher -- fast file discovery, not symbol-level code search.

Self-benchmarked, never vs. a rival →
Atelier vs Serena 0.401 MRR

LSP-wrapped semantic code toolkit -- symbol-level navigation and refactoring via real language servers, 40+ languages.

Self-benchmarked, never vs. a rival →
Atelier vs ripgrep 0.376 MRR

Line-oriented regex search CLI -- no AST or symbol awareness, the fastest possible answer to a text-match question.

Benchmarks itself, not vs. this →
Atelier vs code-index-mcp 0.343 MRR

Tree-sitter AST indexing for 10 core languages, with fallback file indexing for 50+ more.

No published numbers at all →
Atelier vs ast-grep 0.312 MRR

Tree-sitter AST pattern matcher for structural search-and-rewrite -- precise if you already know the exact shape of the code you want.

No published numbers at all →
Atelier vs jCodeMunch 0.299 MRR

Tree-sitter AST symbol retrieval with a compact wire format (MUNCH) -- optimized for token count, not previously measured for match quality.

Self-benchmarked, never vs. a rival →
Atelier vs CodeGraph 0.296 MRR

Local SQLite knowledge graph of symbols, call edges, and dependencies, built via tree-sitter and queried over MCP.

Self-benchmarked, never vs. a rival →
Atelier vs Universal Ctags 0.237 MRR

Tag/definition indexer for editor jump-to-definition -- exact tag lookups only, no free-text or semantic query support.

No published numbers at all →

Methodology, full 13-tool table, and every raw run → BENCHMARKS.md and docs.atelier.ws .