Info

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)

lastfm-64-dot (k = 10)

nytimes-256-angular (k = 10)

Distance: Euclidean

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

sift-128-euclidean (k = 10)

Results by Algorithm

rpforest

BallTree(nmslib)

SW-graph(nmslib)

vamana-pq(diskann)

vamana(diskann)

faiss-ivf

hnswlib

pynndescent

faiss-ivfpqfs

flann

hnsw(vespa)

hnsw(faiss)

n2

milvus

scann

hnsw(nmslib)

annoy

mrpt

puffinn

vald(NGT-panng)

NGT-panng

bruteforce-blas

elastiknn-l2lsh

kgraph

NGT-qg

opensearchknn

NGT-onng

kd

sptag

ckdtree

Contact

ANN-Benchmarks has been developed by Martin Aumueller (maau@itu.dk), Erik Bernhardsson (mail@erikbern.com), and Alec Faitfull (alef@itu.dk). Please use Github to submit your implementation or improvements.