Benchmarking Genomic Selection and Machine-Learning Prediction Models R package GSbench version 0.1.0 A unified interface to fit, cross-validate and benchmark genomic prediction models from SNP marker data. It implements genomic best linear unbiased prediction (GBLUP) and ridge-regression BLUP in base R, and offers a common interface to machine-learning predictors (elastic net, random forest and gradient boosting) through optional packages, together with a stacked ensemble. Cross-validation uses breeding-relevant schemes and reports prediction accuracy honestly, so models can be compared fairly. The genomic relationship matrix follows VanRaden (2008) <doi:10.3168/jds.2007-0980>; the mixed-model solver follows Endelman (2011) <doi:10.3835/plantgenome2011.08.0024>; the genomic-selection framework follows Meuwissen, Hayes and Goddard (2001) <doi:10.1093/genetics/157.4.1819>. Software Depends: R (>= 4.1.0) Imports: graphics, stats, withr Suggests: rrBLUP, glmnet, ranger, xgboost, testthat (>= 3.0.0), knitr, rmarkdown, spelling Muhammad Farooqi <mqfarooqi@gmail.com> Comprehensive R Archive Network (CRAN) Muhammad Farooqi [aut, cre] MIT + file LICENSE (https://CRAN.R-project.org/package=GSbench/LICENSE) 2026-06-30 application/tgz https://CRAN.R-project.org/package=GSbench doi:10.32614/CRAN.package.GSbench en-GB