Large Language Models (LLMs) have demonstrated the potential to generalize across modalities and domains. With their in-context learning (ICL) capabilities, LLMs can perform predictive tasks over structured inputs without explicit fine-tuning. In this work, we investigate the empirical prediction capability of LLLMs on small-scale structured datasets for classification, regression and clustering tasks. We evaluate the performance of state-of-the-art LLMs (GPT, Gemini, DeepSeek) under few-shot prompting and compare them against machine learning (ML) baselines, including tabular foundation models (TFMs). Our results show that LLMs achieve strong performance in classification tasks, establishing zero-training baselines. In contrast, the performance in regression is poor compared to ML models, likely because regression demands outputs in a large space, and clustering results are similarly limited, which we attribute to the absence of genuine ICL in this setting. Nonetheless, this approach enables low-overhead data analysis and offers a viable alternative to traditional ML pipelines. We further analyze the influence of context size and prompt structure on predictive performance. Our findings suggest that LLMs can serve as general-purpose predictive engines for structured data, with clear strengths in classification and significant limitations in regression and clustering.