COVID-19 has been notoriously unpredictable in its clinical course. Such unpredictability poses a challenge to clinicians in predicting patients who will develop severe cases and possibly die from the infection. This study aims to assess and compare the diagnostic value of the NLR and SII as biomarkers in predicting COVID-19 severity, represented by mortality, with a multicentre comparative study including 855 patients in Saudi Arabia. Descriptive and analytical statistics were used to compare haematological indices between survivors and non-survivors. The median age of patients included was 41 years old, with an almost equal ratio of men to women. Most participants were Saudis, and the mortality rate in the study cohort was 13.22%. Non-survivors, as compared to survivors, were significantly older, had lower RBC counts, haemoglobin and haematocrit levels, as well as significantly higher WBC and neutrophil counts. Both the NLR and SII were capable of differentiating between survivors and non-survivors, with the latter having significantly higher values. However, the NLR was superior to the SII in such differentiation, as it had a larger area under the curve. This study further confirms the diagnostic values of the NLR and SII as biomarkers in predicting COVID-19 severity and mortality, with the NLR being more sensitive and specific. Clinical guidelines on managing COVID-19 cases should benefit from these findings by harnessing the value of the NLR in COVID-19 management.