The simulation, assessment, and harvesting of maximum energy of the solar photovoltaic (PV) system require accurate and fast parameter estimation for solar cell/module models. No complete information on the PV module parameters is provided in the manufacturer’s datasheets. This leads to a nonlinear PV model with a number of unknown parameters. Recently, a new meta-heuristic algorithm called equilibrium optimizer (EO) is suggested to solve global problems. However, the EO is trapped to local optima when it is applied to real-world problems. Therefore, this paper proposes a novel and efficient algorithm called opposition-based equilibrium optimization (OBEO) for extracting the parameters of various PV models, including the single-diode model (SDM), double-diode model (DDM), and three-diode model (TDM). This paper presents opposition-based learning as an update mechanism to produce the best solutions to find better search space. In this paper, the PV module parameters are extracted using three distinct points: open-circuit voltage, V_oc, short-circuit current, I_sc, and the point at which maximum power in the I–V curve is provided by the datasheet. The proposed OBEO algorithm minimizes the error of the I–V relationship, and the OBEO algorithm helps to find the optimal solution by generating zero error, and the search agent updates the position randomly with respect to the best solution to reach the optimal state. The proposed algorithm optimizes the parameters of the module without any assumptions. Finally, the proposed method of extracting the parameter is compared with the state-of-the-art methods to validate its performance. The proposed OBEO can achieve zero error values (fitness values) for all PV models, and the average runtime of the OBEO is 14.78?s, 28.33?s, and 32.62?s for SDM, DDM, and TDM, respectively, of all selected PV modules.