AI Paper Atlas

Research map / Large language models / Agents, code and math

K-12EduBench: A Benchmark for Evaluating Large Language Models’ Knowledge, Problem-Solving, and Educational Goal Cognition in K-12 Education

Yuqing Ye, Xuan Zhou, Zhifu Chen, Dandan Li, Hengnian Gu, Jin Peng Zhou, Dongdai Zhou

AAAI 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use education-optimized EduChat-R1-32B rather than under-scaled education-optimized EduChat-SFT-13Beducation-optimized LLMs · K-12EduBench compositeavg composite score: 19.64 -> 71.41Improved
use education-optimization at sufficient scale vs general-purpose modelsLLMs · K-12EduBench composite rankrankMixed
add reasoning-focused training (DeepSeek-R1 vs DeepSeek-V3)DeepSeek · K-12EduBench compositeavg composite score: 79.67 -> 69.13Hurt
judge by knowledge ability theta instead of accuracyLLM rankings · K-12EduBenchcorrelation: theta vs ACC 0.801-0.992No clear effect
compare problem-solving ability with knowledge abilityLLMs · K-12EduBenchPearson r (theta vs rho): 0.653-0.879 (positive)Improved
use LLMs for Bloom cognitive level classification instead of random guessall LLMs · Bloom classificationMAE: 1.65 -> 0.81 (best)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy