Sulfentrazone is one of the main pre-emergent herbicides used in tobacco plantations. The objective of this work was to evaluate the selectivity and efficiency of sulfentrazone-based formulations in two tobacco production systems (conventional tillage system [CTS] and no-tillage system [NTS]). Two experiments were conducted (CTS and NTS) in a randomized block design, with seven treatments and four replications. The herbicide treatments were: T1 = Boral® 500 SC (400 g∙ha^-1 of sulfentrazone), T2 = PonteiroBR® (400 g∙ha^-1 of sulfentrazone), T3 = Stone® (350 + 700 g∙ha^-1 of sulfentrazone and diuron, respectively), T4 = Boral® 500 SC + Gamit® 360 CS (792 g∙ha^-1 of clomazone), T5 = PonteiroBR® + Gamit® 360 CS, T6 = Stone® + Gamit® 360 CS, and T7 = control (manual weeding). Phytotoxicity in tobacco plants and weed control efficiency were visually evaluated 14, 28, 42, and 56 days after application (daa) of the treatments. Emerged weed plants per m2 were counted 56 daa. Tobacco yield was evaluated by determining the yield per third of the plant (lower, middle, and upper thirds) and the total yield (sum of the yields from each third). The sulfentrazone formulations were efficient in weed control. The herbicide Stone® applied alone or mixed with Gamit® caused mild phytotoxicity in plants under NTS, but no yield losses. No significant difference was found in yield among treatments; however, the yield of the upper third of the plant was higher for plants under NTS, affecting the total yield. The sulfentrazone formulations used provided efficient weed control and selectivity to tobacco plants. The use of NTS resulted in higher yields.