The Genome Taxonomy Database Toolkit (GTDB-Tk) is a computational tool designed to provide objective taxonomic assignments for bacterial and archaeal genomes based on the Genome Taxonomy Database (GTDB). GTDB-Tk is efficient and can classify thousands of draft genomes in parallel. The tool uses domain-specific, concatenated protein reference trees and evaluates genomes based on their placement in these trees, relative evolutionary divergence (RED), and average nucleotide identity (ANI) to determine taxonomic ranks. The accuracy of GTDB-Tk's taxonomic assignments is evaluated using a diverse set of 10,156 metagenome-assembled genomes (MAGs). The results show that GTDB-Tk generally agrees with manual curation, with most disagreements being at the rank difference level. GTDB-Tk is available as an online resource and a standalone tool, serving as a valuable resource for classifying microbial genomes from metagenomic datasets.The Genome Taxonomy Database Toolkit (GTDB-Tk) is a computational tool designed to provide objective taxonomic assignments for bacterial and archaeal genomes based on the Genome Taxonomy Database (GTDB). GTDB-Tk is efficient and can classify thousands of draft genomes in parallel. The tool uses domain-specific, concatenated protein reference trees and evaluates genomes based on their placement in these trees, relative evolutionary divergence (RED), and average nucleotide identity (ANI) to determine taxonomic ranks. The accuracy of GTDB-Tk's taxonomic assignments is evaluated using a diverse set of 10,156 metagenome-assembled genomes (MAGs). The results show that GTDB-Tk generally agrees with manual curation, with most disagreements being at the rank difference level. GTDB-Tk is available as an online resource and a standalone tool, serving as a valuable resource for classifying microbial genomes from metagenomic datasets.