Accurate predictions of herbicide dissipation endpoints are essential for making environmental management decisions, estimating the duration of weed control, and deciding crop replant and rotation options. The performance of the single first‐order (SFO), first‐order multiple‐compartment (FOMC), bi‐exponential (BEXP), first‐order double‐exponential decay (FODED), and first‐order two‐compartment (FOTC) was evaluated to describe S‐metolachlor dissipation. Results showed that the BEXP and FOTC were not appropriate. The FODED was ranked as the top model with the lowest Akaike's information criterion (AICc) value among the other three candidate models and was followed by the FOMC model. The SFO displayed the largest root mean square error (11.43) and mean absolute error (9.16) values, and the smallest Nash–Sutcliffe efficiency value (0.88) within the set of three appropriate candidate models. The SFO predicted a time it takes the herbicide to dissipate to one‐eighth of its original concentration, 21 and 26 days shorter than that predicted by the FOMC and FODED, respectively. The SFO also predicted a time for S‐metolachlor to dissipate to one‐tenth of its original concentration, 33 days shorter than that predicted by both FOMC and FODED. Therefore, even though the SFO is effective at predicting half‐life, caution might be required when making inferences about DT90 or the time required for the dissipation of 90% of the initial concentration of pesticides in the soil using the SFO.