In this work, we studied four types of cosmological models with different mechanisms driving the accelerated expansion of the universe, include Braneworld models, Chaplygin Gas models, Emergent Dark Energy models, and cosmological torsion models. Considering that the dynamics of these models at low redshifts are very similar and difficult to distinguish, we used the latest and largest UV and X-ray measurements of quasars (QSOs) observations covering the range of redshift 0.009<z<7.5\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$0.009<z<7.5$$\\end{document}. However, the high intrinsic dispersion of this sample and the degeneracy between cosmological model parameters, we added 2D-BAO and 3D-BAO datasets to help us constrain the parameters of these cosmological models. Our results suggest that standard cold dark matter scenario may not be the best cosmological model preferred by the high-redshift observations. The Generalized Chaplygin Gas (GCG) and cosmological constant plus torsion (named Case II) models perform best by Akaike Information Criterion (AIC), but the Λ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Lambda $$\\end{document}CDM is the best cosmological model preferred by Bayesian Information Criterion (BIC). Our work also supports that the Phenomenologically Emergent Dark Energy and cosmological torsion models may alleviate the Hubble tension, the reported value of the Hubble constant obtained from QSO+BAO datasets combination lies between Planck 2018 observations and local measurements from the SH0ES collaboration, while other cosmological models all support that the Hubble constant tends to be closer to recent Planck 2018 results, but these model are penalized by information criterion.