Due to the lack of lysimetric data in many regions, the standard Penman‐Monteith equation adopted FAO (FAO56‐PM model) is usually used for calculating the reference evapotranspiration (ETo). However, as this model needs lots of meteorological parameters that cannot be easily obtained in many regions, other simple models along with the soft computing models are used for obtaining ETo values. The current paper presents a comprehensive comparison of 12 soft computing models, gene expression programming (GEP), neuro fuzzy with grid partitioning (NF‐GP), neuro fuzzy with sub‐clustering (NF‐SC), multi‐variate adaptive regression spline (MARS), boosted regression tree (BT), random forest (RF), model tree (MT), support vector machine (SVM), SVM‐firefly algorithm (SVM‐FA), extreme learning machine (ELM), neural network‐particle swarm optimization (NN‐PSO) and neural network‐differential evolution (NN‐DE), for estimating daily ETo values in humid regions. So, daily meteorological data from two weather stations (during a 12‐years period) were used to assess the models. The obtained results revealed that a very good efficiency was obtained from all the applied methods. The temperature‐based SVM‐FA (root mean square error, RMSE = 0.324 mm and Nash‐Sutcliffe coefficient, NS = 0.960) and NF‐GP (RMSE = 0.272 mm and NS = 0.974) models generally provided the best accuracy in estimating ETo of Sari and Bablosar, respectively. The accuracy ranks of the other models (from the best to worst) were found as NN‐PSO, NF‐SC, ELM, NN‐DE, MARS, GEP, RF, SVM, BT and MT. Among the radiation‐based models, the NF‐GP provided the best accuracy in estimating ETo of both stations. The other models were ranked as ELM, SVM‐FA, NN‐DE, NN‐PSO, MARS, RF, BT, NF‐SC, SVM and MT, respectively. This article is protected by copyright. All rights reserved.