In the current work, the activated biosorbent prepared from Calcined Cow Leather (CCL) was used to study the biosorption potential on anti-inflammatory, namely Sodium Diclofenac and derived from phenylacetic acid from the group of arylcarboxylic acids. Thus, it has been selected because they are widely used and potential associated toxicological effects and also apparently detected in aqueous environments. The biosorption study was carried out to examine the biosorption mechanism by applying the five isotherms models represented by the Langmuir, Freundlich, Elovich, Temkin and Dubinin-Radushkevich. The comparison of linear and nonlinear regression methods was applied by taking into consideration mathematical and statistical properties of these two methods and compare different statistical criteria to determine the best model fitted to experimental data by predicting the optimum isotherms parameters. The following six error functions were used, the coefficient of determination (R²), the sum of the squares of the errors (SSE), Hybrid fractional error function (HYBRID), Average relative error (ARE), Sum of the absolute errors (SAE) and Marquardt’s percent standard deviation (MPSD). Whereas, the comparison between different models shows that the nonlinear form of Langmuir model was the best fitted to describe the equilibrium data which was confirmed by the five error functions and the smallest ‘sum of the normalized errors (SNE)’ parameter. Therefore, the kinetics data was evaluated by various models. It was found that the biosorption process was conducted by the pseudo-second-order model which predicted best the experimental data.