This study investigates the creative capacities of artificial intelligence (AI), exemplified by ChatGPT-4, in comparison with human creativity, utilizing the Figural Interpretation Quest (FIQ) as the evaluative tool. The primary objective is to assess whether AI can surpass human performance in creative tasks, particularly in terms of flexibility and subjectively perceived creativity. Participants, including both ChatGPT-4 and humans, were asked to provide creative interpretations for a set of ambiguous, abstract figures. The study measured the flexibility of these interpretations and gathered subjective ratings of creativity from independent evaluators. Results indicated that while AI, on average, demonstrated higher flexibility in generating creative interpretations, human participants excelled in terms of subjectively perceived creativity. Furthermore, the most creative human responses were higher than those of AI in both flexibility and subjective creativity. These findings suggest that in these types of complex multimodal interpretation tasks, AI shows excellent potential and the ability to generate semantically diverse ideas, yet human subjectively perceived creativity remains for now unmatched. The study highlights the limitations of AI in replicating the complexity of human creativity and points to possible theoretical interpretations of the reported findings.