K12-Bench

Product or Programme · All products and programmes
Evidence · 2 claims (2 for) · 2 studies (2 design), q2 · 0 of 2 report an effect size · 2 claims rest on one study

Description

K12-Bench is a 23,640-item multi-select benchmark dataset created by Hao Liang et al. for evaluating large language models' structural understanding of K–12 curricula.

Components

Claims

• OmniEdu-27B achieves the best overall curriculum-grounding performance among evaluated models, raising K12-Bench EM from 52.11% to 63.12% [+W]
• Current LLMs lack robust curriculum cognition: even the best model reaches only 57.1% exact match on K12-Bench, with prerequisite and neighbor tasks hardest [+W]

Related Products and Programmes

• K12-KGraph
• K12-Train

Key Sources

• Hao Liang, Qihan Lin, Mingrui Chen, Hengyi Feng, Zhaoyang Han, Xiaochen Ma, Zhen Hao Wong, Meiyi Qiang, Linzhuang Sun, Wentao Zhang. (2026). K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs. arXiv preprint. https://arxiv.org/abs/2605.09635

Page metadata

Field	Value
type	product
id	k12-bench
title	K12-Bench
description	K12-Bench is a 23,640-item multi-select benchmark dataset created by Hao Liang et al.
status	review
product_kind	dataset
generated	by process:settle-candidates on 2026-10-11
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.