Background and Objective Head and neck cancer is a malignant tumor that begins in the head and neck region, and has the sixth highest incidence worldwide. Previous studies have indicated several prognostic markers for head and neck squamous cell carcinoma (HNSCC), but due to poor accuracy and sensitivity of these clinical characteristic markers attention has been gradually switched to molecular biomarkers. This study aimed to sort out the mRNAs correlated with patient survival time to establish an mRNA combination prognostic biomarker model for HNSCC patient risk stratification, providing optimal therapeutic regimens and improving patient prognosis. Methods Clinical data and transcriptome sequencing data of HNSCC were retrieved from TCGA database and were allocated into training and validation datasets. The prognostic model was established using the mRNAs, which were sorted out from training dataset by a significant correlation with survival time. Eventually, the prediction property of the model was evaluated by Kaplan-Meier survival analysis and receiver operating characteristic (ROC) curve. Results An optimal prognostic model by the combination of six mRNAs was established. Kaplan-Meier survival analysis revealed effective risk stratification by this model for patients in the two datasets. The area under ROC curve (AUC) was [ 0.65 for training and validation datasets, indicating good sensitivity and specificity of this model. Moreover, prominent superiority of this model to investigate prognostic biomarkers was demonstrated. Conclusion Our model provided effective prognostication in terms of death risk stratification and evaluation in HNSCC patients. Combination of this prognostic model with current treatment measures is expected to greatly improve the patients' prognosis. Keywords Biomarkers Á Survival time Á Cox regression Á Kaplan-Meier survival analysis Shrikant Pawar and Aditya Stanam have contributed equally to this work.