From Canonical to Complex: Benchmarking LLM Capabilities in Undergraduate Thermodynamics
This work addresses the need for reliable AI tutoring in science education, but it is incremental as it benchmarks existing models without proposing new methods.
The researchers tackled the problem of evaluating large language models' readiness for unsupervised tutoring in undergraduate thermodynamics by creating the UTQA benchmark, finding that no leading 2025-era model exceeded a 95% competence threshold, with the best achieving 82% accuracy and struggling particularly in image reasoning tasks.
Large language models (LLMs) are increasingly considered as tutoring aids in science education. Yet their readiness for unsupervised use in undergraduate instruction remains uncertain, as reliable teaching requires more than fluent recall: it demands consistent, principle-grounded reasoning. Thermodynamics, with its compact laws and subtle distinctions between state and path functions, reversibility, and entropy, provides an ideal testbed for evaluating such capabilities. Here we present UTQA, a 50-item undergraduate thermodynamics question answering benchmark, covering ideal-gas processes, reversibility, and diagram interpretation. No leading 2025-era model exceeded our 95\% competence threshold: the best LLMs achieved 82\% accuracy, with text-only items performing better than image reasoning tasks, which often fell to chance levels. Prompt phrasing and syntactic complexity showed modest to little correlation with performance. The gap concentrates in finite-rate/irreversible scenarios and in binding visual features to thermodynamic meaning, indicating that current LLMs are not yet suitable for unsupervised tutoring in this domain.