With the increasing interest and enrollment of students in higher education, academics must spend significant time providing feedback and evaluations. This study attempts to study the use of generative artificial intelligence (GenAI) tools in assessment and giving feedback. The primary aim is to examine how effective GenAI tools are in evaluating and providing feedback, especially for open-ended text-based questions. A case study was conducted using 50 students who follow a foundation program in computing at a leading university in Sri Lanka. A proctored online examination was set up in a controlled environment, and answers were evaluated using ChatGPT, Gemini, and manual methods. The evaluation was carried out using common rubrics in all three methods mentioned above, and marks generated and given were compared using all three evaluation methods. Interestingly, the results show that compared to ChatGPT and Gemini, evaluation results are much closer to the marks manually given by using manual marking. The ChatGPT and Gemini as GenAI tools generated answers are also closer to each other. The findings prove that we can use GenAI tools effectively to evaluate structured examinations and provide feedback based on pre-defined rubrics. This will reduce the significant time taken for the evaluation and improve the productivity of academics.