Post-Silicon Validation is a crucial part of manufacturing chips, which is an important component in our daily life, but the validation is still a challenging task. With the recent rising popularity and advancement of Large Language Models, the opportunity is given to evaluate and explore its capabilities to tackle Post-Silicon Validation Tuning. To do so, this study determines the current best Large Language Model out there with benchmark problems, which is then tested and evaluated as an optimizer for the Post- Silicon Validation Tuning. Even if the model’s performance is not as desired as an optimizer for PSV Tuning, Large Language Models still show promising capabilities and behaviour. Therefore one can still stay hopeful, that Large Language Models may be capable of optimising Post-Silicon Validation Tuning instances in the future.