We perform the first mapping of the ideological positions of European parties using generative Artificial Intelligence (AI) as a “zero-shot” learner. We ask OpenAI's Generative Pre-trained Transformer (GPT-3.5) to identify the more “right-wing” option across all possible duplets of European parties at a given point in time, solely based on their names and country of origin. Following Wu et al. (2023), we combine this information via a Bradley-Terry decomposition to create an ideological ranking. A comparison of our LLM-generated assessment with widely-used expert-, manifesto- and survey-based measures reveals that Large Language Models (LLMs) may provide a reliable, cost- and time-effective option for researchers to map the evolution of parties' ideological stand in real-time.