EduIllustrate is a benchmark of 230 K-12 STEM problems that evaluates LLMs on interleaved text-diagram generation using sequential anchoring and an 8-dimension rubric, with Gemini 3.0 Pro Preview scoring highest at 87.8%.
right answer, wrong method
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EduIllustrate: Towards Scalable Automated Generation Of Multimodal Educational Content
EduIllustrate is a benchmark of 230 K-12 STEM problems that evaluates LLMs on interleaved text-diagram generation using sequential anchoring and an 8-dimension rubric, with Gemini 3.0 Pro Preview scoring highest at 87.8%.