> ## Documentation Index
> Fetch the complete documentation index at: https://docs.learningcommons.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Overview of Text Complexity evaluators that measure qualitative text complexity, from sentence structure and vocabulary to grade-level fit.

<EarlyAccess isBreaking={false} />

## The problem

[Research](https://achievethecore.org/content/upload/Research%20Supporting%20the%20ELA%20Standards%20and%20Shifts%20Final.pdf) ↗ 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 Text Complexity evaluators assess text across multiple qualitative dimensions.

They are anchored in Student Achievement Partners (SAP)'s [Qualitative Text Complexity Rubric for Informational Text](https://learnwithsap.b-cdn.net/app/uploads/2026/04/Qualitative-Text-Complexity-Rubric-Informational.pdf) ↗, 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

| Evaluator | <Tooltip tip="Student Achievement Partners">SAP</Tooltip> rubric dimension | Description |
| :- | :- | :- |
| **[Grade Level Appropriateness](/evaluators/text-complexity-evaluators/grade-level-appropriateness)** | All dimensions | Determines whether AI-generated text is suitable for a grade band and suggests scaffolding that can support instruction of the text |
| **[Background Knowledge Demands](/evaluators/text-complexity-evaluators/background-knowledge-demands)** | Subject Matter Knowledge | Identifies the background knowledge a student needs to comprehend the generated text |
| **[Vocabulary Complexity](/evaluators/text-complexity-evaluators/vocabulary-complexity)** | Vocabulary | Measures how challenging students may find the vocabulary of AI-generated texts |
| **[Sentence Structure](/evaluators/text-complexity-evaluators/sentence-structure)** | Sentence Structure | Assesses the complexity of sentence structure in informational texts relative to a specified grade level |
| **[Meaning Directness](/evaluators/text-complexity-evaluators/meaning-directness)** | Conventionality | Analyzes how directly a text communicates its meaning |
| **[Purpose Clarity](/evaluators/text-complexity-evaluators/purpose-clarity)** | Purpose | Assesses how clearly a text communicates its central purpose, and identifies elements that make that purpose accessible or challenging to readers |
| **[Organizational Structure](/evaluators/text-complexity-evaluators/organizational-structure)** | Organization | Assesses how demanding a text's organizational structure is for students at a given grade level |
| **[Reference Knowledge Demands](/evaluators/text-complexity-evaluators/reference-knowledge-demands)** | Intertextuality | Assesses what a text assumes you've already encountered and then builds on to create meaning |

Explore our [Text Complexity dataset](/evaluators/dataset/text-complexity) for the benchmark data that our Text Complexity evaluators use to assess text complexity.

## Scope and limitations

<Warning>
  Text Complexity evaluator outputs should not be used for high-stakes
  applications like grading, assessment, or placement decisions without human
  review.
</Warning>

Remember that LLM scores can vary across runs, especially on borderline cases.
We recommend keeping a human in the loop and treating outputs as directional
signals vs. definitive judgments.

## Related topics

<CardGroup cols={2}>
  <Card title="Text Complexity dataset" icon="database" href="/evaluators/dataset/text-complexity">
    Explore the expert-annotated benchmark behind Text Complexity evaluators.
  </Card>

  <Card title="SDK API Reference" icon="code" href="/evaluators/sdk-api-reference/overview">
    Integrate Text Complexity evaluators into your TypeScript or Python project.
  </Card>

  <Card title="Feedback evaluators" icon="message" href="/evaluators/feedback-evaluators/introduction">
    Explore evaluators that assess the quality of coaching feedback.
  </Card>

  <Card title="Academic Standards evaluators" icon="certificate" href="/evaluators/academic-standards-evaluators/introduction">
    Explore evaluators that assess content alignment to academic standards.
  </Card>
</CardGroup>