Can a large language model accurately solve a university-level microeconomics exercise on health insurance? We tested Manus AI on a multi-part problem involving demand curves, list prices, out-of-pocket prices, and the calculation of social loss under various insurance schemes – including full insurance, coinsurance, and copayment plans. Not only did the
Argument mapping is a useful method for visualising the logical structure of reasoning, particularly in complex or multi-step arguments. In this post, we examine how Claude 3.7 Sonnet performs when prompted to identify the structure of arguments and represent them visually. The model was given five tasks, each involving
Creating visualisations from raw meteorological data no longer requires programming skills. In this post, we demonstrate how researchers can generate a warming stripes diagram – a simple yet powerful visualisation of long-term temperature trends – using only a natural language prompt. We recommend using GPT-4o or GPT-4.5 for this task, as
In earlier explorations, we identified the GenAI models that appeared most promising for data visualisation tasks—models that demonstrated strong code generation capabilities, basic support for data wrangling, and compatibility with popular Python libraries such as Matplotlib and Seaborn. In this follow-up case study, we examine a different dimension: rather
Except for Claude 3.7 Sonnet, GPT-4o and GPT-4.5 (which we discussed in a separate post), all other GenAI models we tested encountered issues when asked to generate a simple bar chart from a CSV file. The limitations varied widely—from difficulties in reading the file and missing visualisation
As data visualisation becomes an increasingly integral part of communicating research and insights, the choice of generative AI models capable of handling both code and chart rendering has never been more important. In this post, we explore which models can be reliably used for visual tasks—such as generating Python-based
