Paul Atherton

Mohamed Huti, Alasdair Mackintosh, Amy Waldock et al.

AI models have achieved state-of-the-art results in textual reasoning; however, their ability to reason over spatial and relational structures remains a critical bottleneck -- particularly in early-grade maths, which relies heavily on visuals. This paper introduces the visual reasoning benchmark (VRB), a novel dataset designed to evaluate Multimodal Large Language Models (MLLMs) on their ability to solve authentic visual problems from classrooms. This benchmark is built on a set of 701 questions sourced from primary school examinations in Zambia and India, which cover a range of tasks such as reasoning by analogy, pattern completion, and spatial matching. We outline the methodology and development of the benchmark which intentionally uses unedited, minimal-text images to test if models can meet realistic needs of primary education. Our findings reveal a ``jagged frontier'' of capability where models demonstrate better proficiency in static skills such as counting and scaling, but reach a distinct ``spatial ceiling'' when faced with dynamic operations like folding, reflection, and rotation. These weaknesses pose a risk for classroom use on visual reasoning problems, with the potential for incorrect marking, false scaffolding, and reinforcing student misconceptions. Consequently, education-focused benchmarks like the VRB are essential for determining the functional boundaries of multimodal tools used in classrooms.

Maxime Lelièvre, Amy Waldock, Meng Liu et al.

Benchmarks like Massive Multitask Language Understanding (MMLU) have played a pivotal role in evaluating AI's knowledge and abilities across diverse domains. However, existing benchmarks predominantly focus on content knowledge, leaving a critical gap in assessing models' understanding of pedagogy - the method and practice of teaching. This paper introduces The Pedagogy Benchmark, a novel dataset designed to evaluate large language models on their Cross-Domain Pedagogical Knowledge (CDPK) and Special Education Needs and Disability (SEND) pedagogical knowledge. These benchmarks are built on a carefully curated set of questions sourced from professional development exams for teachers, which cover a range of pedagogical subdomains such as teaching strategies and assessment methods. Here we outline the methodology and development of these benchmarks. We report results for 97 models, with accuracies spanning a range from 28% to 89% on the pedagogical knowledge questions. We consider the relationship between cost and accuracy and chart the progression of the Pareto value frontier over time. We provide online leaderboards at https://rebrand.ly/pedagogy which are updated with new models and allow interactive exploration and filtering based on various model properties, such as cost per token and open-vs-closed weights, as well as looking at performance in different subjects. LLMs and generative AI have tremendous potential to influence education and help to address the global learning crisis. Education-focused benchmarks are crucial to measure models' capacities to understand pedagogical concepts, respond appropriately to learners' needs, and support effective teaching practices across diverse contexts. They are needed for informing the responsible and evidence-based deployment of LLMs and LLM-based tools in educational settings, and for guiding both development and policy decisions.

Daniel Björkegren, Jun Ho Choi, Divya Budihal et al.

Although 85% of sub-Saharan Africa's population is covered by mobile broadband signal, only 37% use the internet, and those who do seldom use the web. The most frequently cited reason for low internet usage is the cost of data. We investigate whether AI can bridge this gap by analyzing 40,350 queries submitted to an AI chatbot by 469 teachers in Sierra Leone over 17 months. Teachers use AI for teaching assistance more frequently than web search. We compare the AI responses to the corresponding top search results for the same queries from the most popular local web search engine, google.com.sl. Only 2% of results for corresponding web searches contain content from in country. Additionally, the average web search result consumes 3,107 times more data than an AI response. Bandwidth alone costs \$2.41 per thousand web search results loaded, while the total cost of AI is \$0.30 per thousand responses. As a result, AI is 87% less expensive than web search. In blinded evaluations, an independent sample of teachers rate AI responses as more relevant, helpful, and correct than web search results. These findings suggest that AI-driven solutions can cost-effectively bridge information gaps in low-connectivity regions.