Can state-of-the-art multimodal models analyse animal behaviour directly from video footage? In this study, we tested Google’s Gemini 2.5 Pro — both in AI Studio and via its API — to assess whether it can produce structured ethological descriptions based purely on short animal-related videos. By applying a consistent prompt
Recent advancements in multimodal language models have opened new avenues for analysing scientific image data using natural language instructions. In this post, we explore the capabilities of OpenAI’s o4-mini-high model for performing cell segmentation tasks on microscopy images through prompt-based interaction. Rather than relying on traditional computer vision techniques
Identifying specific clinical findings in unstructured medical texts is a common challenge in healthcare data science. In this post, we benchmark Google’s Gemini 2.5 Flash language model on a zero-shot classification task: detecting the presence or absence of distal fibula fractures in real-world German radiology reports. Without any
We assessed the ability of Claude 4 Sonnet and GPT-4o to classify brain MRI images as healthy or tumorous for research labelling purposes, using both the chat interface (10 images) and the API (125 images). Claude 4 Sonnet achieved perfect accuracy (10/10) in chat, but its API refused to
Prompt-based methods are becoming increasingly relevant in biomedical text mining, offering flexible ways to perform tasks such as named entity recognition without explicit model training. In this case study, we assess the performance of DeepSeek-V3 on a structured disease mention extraction task using a curated subset of the NCBI Disease
How well can today’s leading GenAI models classify real-world biodiversity data—without bespoke code or traditional machine learning pipelines? In this study, we benchmarked a range of large language models on the task of predicting penguin species from tabular ecological measurements, including both numerical and categorical variables. Using a
How far can today’s large language models go in scientific data analysis—without bespoke coding or deep learning pipelines? In this experiment, we explore the ability of DeepSeek-V3 to perform pixel-level detection of Argania trees (i.e., binary classification for each pixel) using only tabular Sentinel-2 spectral data. By
Working with real-world text data often means dealing with structures that are not yet analysis-ready. In our case, the dataset included headlines and full article texts stored separately, across two different tables. The only link between them was a shared identifier field: Body ID. Before we could begin any further
Image-based classification is increasingly used across biology, ecology, and agriculture—from identifying animal species to detecting plant diseases. One common use case is the analysis of leaf images to distinguish between healthy and diseased plants. In this post, we compare two approaches to classifying strawberry leaves as either fresh (healthy)
Working with biomedical corpora often requires programming skills, specialised formats, and time-consuming preprocessing. But what if you could transform a complex annotated dataset—like the NCBI Disease Corpus—into a structured, analysis-ready CSV using nothing more than a single, well-designed prompt? In this post, we demonstrate how a no-code, GenAI-powered
Having previously explored the FutureHouse Platform’s agents in tasks such as identifying tailor-made laws and generating a literature review on legislative backsliding, we now directly compare its Falcon agent and OpenAI’s o3. Our aim was to assess their performance on a focused literature search task: compiling a ranked
Generative AI has made extraordinary strides in recent years, reshaping how researchers write, code, and even analyse data. But a key question remains for academics hoping to automate more of their daily work: Can popular GenAI models like Copilot, Claude 3.7 Sonnet, Gemini 2.0 Flash, GPT-4o, Grok 3
