Background: In the last few decades, different coma scoring scales have been proposed. The purpose of this study is to compare two coma scales: the GCS (Glasgow Coma Scale) and the FOUR score (Full Outline of UnResponsiveness score), aiming to examine which scale is better in predicting mortality outcome in traumatic brain injury (TBI) patients in the prehospital setting. Methods: We evaluated the GCS and FOUR score in the prehospital setting at three different prehospital timepoints, and we reassessed the scores in surviving patients 24 hours, one month and three months after the injury. Then, we compared the mortality outcomes. We used the χ² method with the best cut-off point for each model; we calculated sensitivity, specificity and correct prediction of the outcome with four severity scores. The Youden index, Z score, McNemar's test and ROC curve were also assessed. P < 0.05 was considered statistically significant. Both scales were ranked with gain ratio. Results: We included 75 TBI patients who were treated in a prehospital setting by a prehospital specialized medical unit. In terms of predictions of mortality, our study showed the following: 1. Twenty-four hours after the injury, the best cut-off points obtained were from the FOUR 2 and FOUR 3 models. 2. One month after the injury, the best cut-off obtained was from the GCS 2 model. 3. Three months after the injury, the best cut-offs obtained were from the GCS 2 and GCS 3 models. Conclusions: In our study, we were able to demonstrate that the FOUR 2 and FOUR 3 models, compared to the GCS 2 and GCS 3 models, resulted in only a marginally better prediction of mortality outcome 24 hours after TBI. Statistically significant differences were found in neither the Youden index nor the area under the ROC curve after 24 hours and one and three months after the injury.