Skip to main content

The problem

Research ↗ shows that students who consistently engage with complex texts are more likely to succeed in college and beyond. Yet despite their importance, complex texts often remain absent from classrooms.
  • Quantitative measures of text complexity (e.g., Lexile or Flesch-Kincaid) are useful, but limited
  • Qualitative measures are more accurate, but also more labor-intensive to assess
As AI-generated texts enter the classroom, educators risk using content that looks grade-appropriate on the surface, but fails to meet the deeper demands of literacy development.

What we’re building

Instead of giving a single complexity score, our literacy evaluators assess text across multiple qualititative dimensions. They are anchored in Student Achievement Partners’ Qualitative Text Complexity rubric (SAP) ↗, giving you:
  • Fine-grained data to ensure quality generated texts
  • Actionable insights into why a text may be complex or not complex enough and how to best scaffold it for students
EvaluatorDescription
Grade Level Appropriateness Determines whether AI-generated text is suitable for a grade band and suggests scaffolding that can support instruction of the text
Subject Matter Knowledge Identifies the background knowledge a student needs to comprehend the generated text
Vocabulary Measures how challenging students may find the vocabulary of AI-generated texts
Conventionality Analyzes how directly a text communicates its meaning
Purpose Assesses how clearly a text communicates its central purpose, and identifies elements that make that purpose accessible or challenging to readers
Explore our Literacy dataset for the benchmark data that our literacy evaluators use to assess text complexity.