The Cohen's Kappa metric is a statistical measure that quantifies the agreement between two raters when categorizing data, accounting for chance-level matches. It offers a clearer picture of genuine agreement and is invaluable in scenarios where subjective judgment affects data reliability. The metric compares observed agreement with expected agreement, adjusting for random concurrence. Its result ranges between −1 and 1, with practical calculation involving the formula: (observed agreement - expected agreement) / (1 - expected agreement). This metric has been refined over time to accommodate multiple raters and weighted versions for rating scales with varying degrees of disagreement. It is widely applied across critical sectors such as healthcare, psychology, and social sciences, where subjective interpretation can significantly impact data quality. By integrating the Cohen's Kappa metric into AI evaluation frameworks, developers can strengthen their models' performance and make more informed decisions.