ANN-Benchmarks is a benchmarking environment for approximate nearest neighbor algorithms search. This website contains the current benchmarking results. Please visit http://github.com/erikbern/ann-benchmarks/ to get an overview over evaluated data sets and algorithms. Make a pull request on Github to add your own code or improvements to the benchmarking system.

Benchmarking Results

Results are split by distance measure and dataset. In the bottom, you can find an overview of an algorithm's performance on all datasets. Each dataset is annoted by (k = ...), the number of nearest neighbors an algorithm was supposed to return. The plot shown depicts Recall (the fraction of true nearest neighbors found, on average over all queries) against Queries per second. Clicking on a plot reveils detailled interactive plots, including approximate recall, index size, and build time.

Benchmarks for Single Queries

Results by Dataset

Distance: Angular

glove-100-angular (k = 10)

glove-25-angular (k = 10)

nytimes-256-angular (k = 10)

Distance: Euclidean

fashion-mnist-784-euclidean (k = 10)

gist-960-euclidean (k = 10)

sift-128-euclidean (k = 10)

Distance: Hamming

sift-256-hamming (k = 10)

word2bits-800-hamming (k = 10)

Distance: Jaccard

kosarak-jaccard (k = 10)

Results by Algorithm

Algorithms:

faiss-ivf

scann

pgvector

annoy

glass

hnswlib

BallTree(nmslib)

vald(NGT-anng)

hnsw(faiss)

NGT-qg

qdrant

n2

Milvus(Knowhere)

qsgngt

faiss-ivfpqfs

mrpt

redisearch

SW-graph(nmslib)

NGT-panng

pynndescent

vearch

hnsw(vespa)

vamana(diskann)

flann

luceneknn

weaviate

puffinn

hnsw(nmslib)

bruteforce-blas

tinyknn

NGT-onng

elastiknn-l2lsh

sptag

ckdtree

kd

opensearchknn

datasketch

bf

Contact

ANN-Benchmarks has been developed by Martin Aumueller ([email protected]), Erik Bernhardsson ([email protected]), and Alec Faitfull ([email protected]). Please use Github to submit your implementation or improvements.

Info