High-throughput omics technology has revolutionized biomedicine by integrative analyses of various omics layers such as genomics, transcriptomics, proteomics, and epigenomics. Despite the huge progress in this field of study, there are still big challenges to overcome. One of the significant challenges is finding reliable packages for integration of multiple omics. So far, numerous packages have been developed for multi-omics data integration, however there is a lack of benchmarking studies in this area, and more work is needed to evaluate the relative performance of methods. In this study, we focused on evaluating the capabilities of two specific methods, DIABLO and NOLAS, in predicting the survival status of patients. The primary objective was to determine how well these tools can integrate multi-omics data and classify patients based on their survival outcomes. To achieve this, the datasets were first preprocessed to ensure they were suitable for integration. They were then integrated with DIABLO and NOLAS. Finally, the results of DIABLO and NOLAS were evaluated and compared in terms of prediction performance, number of biomarkers, and annotation enrichment analysis. The findings revealed that both DIABLO and NOLAS could not distinguish very clearly between patients who survived and those who did not survive for ten years after cancer diagnosis, which may be due to several factors: including the lack of significant relationships between the selected omics layers (RNA-Seq, miRNA-Seq, RPPA) and survival outcomes, imbalanced datasets, high presence of different proteins and transcription factors in cancer cells, and high heterogeneity and genome instability in omics layers.