Metraipolis › archive › dc_6db5b6daaef2
A Benchmark for LLM's Understanding of Middle School and High School Science Topics — arXiv:2609.32020
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32020
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:55:03.661Z
- SHA-256 of the archived text
8def5fe539c2b7c6fdf50930f422b4c0b8214df20ef1177ffee7c8ac6e988e5f- Stable URL of this page
https://metraipolis.com/documento/dc_6db5b6daaef2
How to cite
A Benchmark for LLM's Understanding of Middle School and High School Science Topics — arXiv:2609.32020 — arXiv (en), https://arxiv.org/abs/2609.32020 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6db5b6daaef2 (Metraipolis archive dc_6db5b6daaef2, sha256 8def5fe539c2b7c6fdf50930f422b4c0b8214df20ef1177ffee7c8ac6e988e5f)
BibTeX
@misc{dc6db5b6daaef2,
title = {A Benchmark for LLM's Understanding of Middle School and High School Science Topics — arXiv:2609.32020},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32020},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6db5b6daaef2; sha256 8def5fe539c2b7c6fdf50930f422b4c0b8214df20ef1177ffee7c8ac6e988e5f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32020. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are increasingly integrated into educational settings, yet educators lack robust, standards-aligned tools to evaluate their effectiveness in K-12 science contexts. Existing benchmarks predominantly assess general language or advanced scientific reasoning, leaving a critical gap in understanding LLMs' performance on content directly relevant to secondary science curricula. To address this gap, we developed a comprehensive NGSS-aligned benchmark for both middle and high school science using a rigorous synthetic data pipeline, multi-judge validation, and item-level psychometric analysis. Nine open-weight LLMs were systematically evaluated using this benchmark, indicating that several smaller, locally deployable models achieved high accuracy across diverse science domains and question types. Our findings indicate that model size did not consistently predict performance, emphasizing the importance of intentional model selection for educational deployment. We then incorporated a human reviewer into the loop, reviewing the items generated by the LLMs for alignment with NGSS standards. The human review indicated that synthetically generated items were not in perfect alignment with the NGSS standards, indicating the benefits of human-in-the-loop item development, the need to explore the intersection of content and pedagogical knowledge, and the need to extend benchmarks to evaluate LLMs' capacity for interactive, evidence-based feedback in educational scenarios. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computers and Society (cs.CY); Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.32020 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:00.695Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).