The electrical characterization of organic semiconductor materials plays a critical role in the design of advanced electronic devices and the understanding of their performance. Particularly, electrical parameters such as the ideality factor, barrier height, and series resistance, derived from the current-voltage (I–V) characteristics of rubrene-based metal-polymer semiconductor (MPS) structures, provide fundamental insights into the material's intrinsic and interfacial properties. The nonlinear nature of these parameters and the uncertainties associated with experimental data render traditional estimation methods inadequate. Additionally, investigating the effects of external factors, especially Cobalt-60 gamma irradiation, on these electrical parameters is of great importance for device reliability. The aim of this study is to accurately and reliably estimate the electrical parameters of Al/rubrene/p-Si Schottky-Junction solar cell using Artificial Intelligence (AI) optimization algorithms, based on experimental I–V data obtained after Cobalt-60 gamma irradiation. In this context, a total of twelve different AI optimization algorithms were employed, including Genetic Algorithm, Differential Evolution, Flower Pollination Algorithm, Artificial Bee Colony, Ant Colony Optimization, Bat Algorithm, Cuckoo Search Algorithm, Grey Wolf Optimization, Jaya Algorithm, Particle Swarm Optimization, Harmony Search, and Teaching-Learning-Based Optimization. The estimation of electrical parameters was performed using I–V measurements conducted across five different forward voltage ranges, with the performance of the algorithms evaluated using MAPE and R² metrics. This study presents that the AI optimization algorithms can be used as optimization tool for parameter estimation of Schottky diode model and the algorithms may offer more effective results compared to traditional optimization methods in the electrical analysis of organic semiconductor models under Cobalt-60 irradiation.