Lexibench: Benchmark Datasets for Computational Historical Linguistics

Lexibench is a collection of benchmark data for computational historical linguistics. If you use the benchmark data assembled here, please cite the dataset: Häuser, Luise; Forkel, Robert; and List, Johann-Mattis (2025): Lexibench. Benchmark Datasets for Computational Historical Linguistics. [Dataset, Version 1.0]. https://codeberg.org/lexibank/lexibench In order to provide more detailed explanations about the data, consider citing the following study introducing Lexibench: Häuser, Luise and List, Johann-Mattis (2025): Lexibench. Towards an Improved Collection of Benchmark Data for Computational Historical Linguistics. Computer-Assisted Language Comparison in Practice 8.1: 9-16. https://doi.org/10.15475/calcip.2025.1.2 The following study introduces PyLexibench, the Python package that we use to populate and update the Lexibench repository: Häuser, Luise; Forkel, Robert; and List, Johann-Mattis (2025): PyLexibench: A Python package for the handling of benchmark data in computational historical linguistics. Computer-Assisted Language Comparison in Practice 8.4: 25-37. https://doi.org/10.15475/calcip.2025.1.4