CSTutorBench: Benchmarking Small Language Models as Tutors for Block-Based Programming
For educators and researchers selecting small language models for K-12 CS tutoring, this benchmark provides a pedagogically grounded evaluation, though findings are preliminary due to limited model sample.
CSTutorBench evaluates small language models as tutors for block-based programming in VEX VR, finding that models perform well on surface-level criteria but struggle with deeper pedagogical behaviors like avoiding answer leakage and engaging with student debugging histories. Prompt revision improved scores for 10 of 11 models.
Large language models are increasingly explored as AI tutors, yet deploying them in K-12 settings raises concerns around privacy, cost, and reliance on proprietary models. Small language models (SLMs) offer a promising alternative, but selecting the right model for a specific educational context remains difficult, particularly when the target domain, such as block-based programming, is largely absent from model training data. We introduce CSTutorBench, a benchmark for evaluating language models as CS tutors in VEX VR, a block-based robotics environment. The benchmark comprises 17 scenario-based questions scored against a pedagogical rubric grounded in established tutoring and feedback research, with a human-in-the-loop LLM-as-judge pipeline for evaluation. Preliminary findings across 11 models (4B-120B parameters) reveal that models perform well on surface-level criteria such as vocabulary and tone but struggle with deeper pedagogical behaviors, particularly avoiding answer leakage and engaging with student debugging histories. In our sample, model family and instruction-tuning approach appear to be better predictors of tutoring quality than parameter count alone, though the small number of models limits the strength of this conclusion. A targeted prompt revision grounded in recent educational prompt engineering research improved scores for 10 of 11 models. These results underscore the value of context-specific, pedagogically grounded benchmarks for SLM selection in educational deployment.