A Benchmark for LLM's Understanding of Middle School and High School Science Topics

arXiv:2609.32020 · cs.AI, cs.CY, cs.HC · Submitted 2026-09-25 · Read on arXiv

cs.AI, cs.CY, cs.HC

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/InviteInstitute/MS-NGSS-Aligned-Benchmark

Terminology

• Benchmark — 105× in this paper · explained in 2 episodes
• Benchmarking — 14× in this paper · explained in 3 episodes
• Accuracy — 11× in this paper · explained in 1 episode
• Alignment — 6× in this paper · explained in 1 episode
• Synthetic Data Generation — 4× in this paper · explained in 5 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• LLM judge — 3× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 3× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Core — 2× in this paper · explained in 2 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Synthetic Data Generation Pipeline — 1× in this paper · explained in 2 episodes

Sources

• LLMs in Education: Novel Perspectives, Challenges, and Opportunities
• LFM2 Technical Report
• The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models
• Large Databases Need Small, Open-Weight Language Models
• Judging the Judges: Human Validation of Multi-LLM Evaluation for High-Quality K--12 Science Instructional Materials
• Measuring Massive Multitask Language Understanding
• Benchmarking the Pedagogical Knowledge of Large Language Models
• 2 OLMo 2 Furious
• TaMPERing with Large Language Models: A Field Guide for using Generative AI in Public Administration Research
• GPQA: A Graduate-Level Google-Proof Q&A Benchmark
• Evaluating the capability of large language models to personalize science texts for diverse middle-school-age learners
• A Survey on Data Synthesis and Augmentation for Large Language Models
• PhysUniBench: A Multi-Modal Physics Reasoning Benchmark at Undergraduate Level
• ELMES: An Automated Framework for Evaluating Large Language Models in Educational Scenarios
• Large Language Models for Education: A Survey
• PhySense: Principle-Based Physics Reasoning Benchmarking for Large Language Models
• Efficient Large Language Models: A Survey

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection