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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use education-optimized EduChat-R1-32B rather than under-scaled education-optimized EduChat-SFT-13B | education-optimized LLMs · K-12EduBench composite | avg composite score: 19.64 -> 71.41 | Improved |
| use education-optimization at sufficient scale vs general-purpose models | LLMs · K-12EduBench composite rank | rank | Mixed |
| add reasoning-focused training (DeepSeek-R1 vs DeepSeek-V3) | DeepSeek · K-12EduBench composite | avg composite score: 79.67 -> 69.13 | Hurt |
| judge by knowledge ability theta instead of accuracy | LLM rankings · K-12EduBench | correlation: theta vs ACC 0.801-0.992 | No clear effect |
| compare problem-solving ability with knowledge ability | LLMs · K-12EduBench | Pearson r (theta vs rho): 0.653-0.879 (positive) | Improved |
| use LLMs for Bloom cognitive level classification instead of random guess | all LLMs · Bloom classification | MAE: 1.65 -> 0.81 (best) | Improved |
Closest papers by meaning
- K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs (NeurIPS 2026 · similarity 0.89)
- CK12: A Rounded K12 Knowledge Graph Based Benchmark for Chinese Holistic Cognition Evaluation (AAAI 2024 · similarity 0.88)
- Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners? (ICML 2024 · similarity 0.87)
- Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study (NeurIPS 2025 · similarity 0.87)
- Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages (ICLR 2025 · similarity 0.86)
- Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process (ICLR 2025 · similarity 0.86)
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.
