Refreshing available models…
all-MiniLM-L6-v2
info
0.50
KeywordSemantic
Used for inline metrics. You can also mark results after searching.
Embench
The retrieval lab
0 total runs
Loading quota…
Which retrieval stack actually works on your data, for your agent?
Embench is a retrieval lab. Index a corpus, run semantic, keyword, hybrid, and reranked search side by side, and see precision, recall, and MRR inline — before your agent depends on it.
Free to use, no signup — quota per browser session.
Explore in the browser, then hand the same harness to your agent: every run here is a plain REST call with a stable JSON contract. CLI for local and CI evals is on the roadmap.
Side-by-side retrieval
Semantic, BM25 keyword, grep, hybrid, and reranked search on the same corpus, in one run.
Evals built in
Mark expected docs and get precision, recall, and MRR next to every result list.
Open-source models
MiniLM, BGE, Qwen, and Stella embeddings plus cross-encoder rerankers. No setup.