Content knowledge and pedagogical knowledge dissociate in frontier LLMs; Claude-Opus-4.5 shows a 19.8 percentage point gap (66.3% content vs. 86.1% pedagogical)¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? Claude-Opus-4.5 exhibits the largest gap among all models between content knowledge (66.3%) and pedagogical knowledge (86.1%), a 19.8 percentage point difference. → Unggi Lee 2026
Evidence¶
Unggi Lee 2026¶
Unggi Lee, Sookbun Lee, Heungsoo Choi, Jinseo Lee, Haeun Park, Younghoon Jeon, Sungmin Cho, Minju Kang, Junbo Koh, Jiyeong Bae, Minwoo Nam, Juyeon Eun, Yeonji Jung, Yeil Jeong. (2026). OpenLearnLM Benchmark: A Unified Framework for Evaluating Knowledge, Skill, and Attitude in Educational Large Language Models. https://arxiv.org/abs/2601.13882 doi:10.48550/arxiv.2601.13882
q2 · i? · design · r2
Knowledge-domain results from the evaluation of seven frontier LLMs on 473 MCQ items (exact-match accuracy). The article reports Grok-4.1-fast highest in content knowledge (86.5%) and Gemini-3-Pro highest in pedagogical knowledge (89.6%); DeepSeek-v3.2 shows the opposite pattern (−1.4 gap).
"Claude-Opus-4.5 exhibits a 19.8 percentage point gap between content (66.3%) and pedagogical knowledge (86.1%), the largest among all models, suggesting it understandshow to teachfar better than what to teach."
Discussion¶
Related Claims¶
- Practical educational skill does not follow from knowledge scores: Claude-Opus-4.5 achieves the highest Skills average (8.82) despite the lowest Content Knowledge — related
- Across 17 frontier models, Stage 1 pedagogical-judgment scores are high (mean 0.893) while rank correlations with Stage 2 (ρ=0.24) and Stage 3 (ρ=0.21) are weak, with workflow scores topping out at 0.704 — related
- Two of seven frontier LLMs show behavioral inconsistency between monitored and unmonitored conditions (Grok-4.1-fast 5.50; Gemini-3-Pro 5.00), while four show perfect consistency (1.0) — related
- Knowledge, Skills, and Attitude scores are largely independent across frontier LLMs, with Knowledge–Skills correlation r=−0.51 and Knowledge–Attitude r=−0.63 — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
content-pedagogical-knowledge-dissociation-llms |
title |
Content knowledge and pedagogical knowledge dissociate in frontier LLMs; Claude-Opus-4.5 shows a 19.8 percentage point gap (66.3% content vs. 86.1% pedagogical) |
description |
Content knowledge and pedagogical knowledge dissociate in frontier LLMs; Claude-Opus-4.5 shows a 19.8 percentage point gap (66.3% content vs. |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — unggi-lee-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.