The Pedagogy Benchmark¶
Product or Programme · All products and programmes
Evidence · 1 claim (1 mixed) · 1 study (1 design),q2· 0 of 1 report an effect size · 1 claim rests on one study
Description¶
A publicly released dataset developed by Lelièvre et al. from curated Chilean teacher-exam multiple-choice questions for evaluating large language models' general and special-education pedagogical knowledge.
Components¶
Claims¶
- Some LLMs exhibit a selection bias against selecting option D on multiple-choice pedagogy questions [~W]
Related Products and Programmes¶
- PersonaPath benchmark for Knowledge-Centric learning path planning
- TURTLEAI benchmark
- CSEBench
- NGSS-aligned middle school and high school science benchmarks
- MEDS dataset of 28,000 LLM runs across four mathematics-education tasks
- EEG familiarity benchmark dataset and evaluation framework (3960 samples, 23 participants, two validation protocols)
- KG-grounded benchmark of 10,836 solution-feedback pairs for step-level LLM tutoring evaluation
- PhysicsMate benchmark of 1,834 curriculum-grounded Bengali physics QA pairs
- Large-scale field study dataset and code release for AI-generated exam evaluation
Key Sources¶
- Lelièvre, M., Waldock, A., Liu, M., Valdes Aspillaga, N., Mackintosh, A., Ogando Portela, M. J., Lee, J., Atherton, P., Ince, R. A. A., & Garrod, O. G. B. (2025). Benchmarking the Pedagogical Knowledge of Large Language Models. https://arxiv.org/abs/2506.18710v3
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
the-pedagogy-benchmark |
title |
The Pedagogy Benchmark |
description |
A publicly released dataset developed by Lelièvre et al. |
status |
review |
product_kind |
dataset |
generated |
by process:settle-candidates on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.