Vocabulary Complexity

Evaluator last updated August 27, 2026.

Overview

The Vocabulary Complexity evaluator gives developers fine-grained vocabulary insights that help ensure texts use words that align with grade-level expectations and support growth in academic language:

Estimates the background knowledge that a student at the target grade level is likely to have
Identifies complex words in the text (Tier 2, Tier 3, archaic, etc.)
Evaluates overall vocabulary complexity relative to the background knowledge estimate

At a glance


Supported grades	3–12
Rubric	Student Achievement Partners (SAP) ↗‘s Qualitative Text Complexity Rubric for Informational Text ↗ (Vocabulary)
Model used	GPT-4o (Step 1), Gemini-2.5-pro (Step 2, Grades 3–4), and GPT-4.1 (Step 2, Grades 5–12) with temperature of 0 The evaluator was built and validated using this specific model and temperature. Other configurations will produce different results and may have lower accuracy.

Getting started

Follow the Quickstart to start using this evaluator:

Access method
Evaluators playground	View in Platform ↗
SDK	Python ↗ and TypeScript ↗
Other	Python notebook ↗ Prompts: `grades-3-4-system.txt` ↗, `grades-3-4-user.txt` ↗, `other-grades-system.txt` ↗, and `other-grades-user.txt` ↗

Inputs

Input	Description	Required
Text	Informational text to evaluate Optimal length: 130-205 words	Yes
Grade level	Target student grade level	Yes

Output

Field	Description
Complexity score	Slightly complex: Uses everyday, familiar vocabulary with few academic or domain-specific terms. Almost entirely contemporary and conversational Very low proportion of complex words (archaic, subject-specific, academic) Easy to understand and does not impede comprehension of the bulk of the text (1-2 quick pauses for processing by the student may occur) Moderately complex: Includes a mix of familiar and academic vocabulary, with some Tier 2 or Tier 3 terms that may require support. Mostly contemporary and conversational Low proportion of complex words (archaic, subject-specific, academic) Generally allows students to comprehend the bulk of the text with little difficulty, though there may be occasional pauses for clarification (several quick pauses or occasional prolonged pauses may occur) Very complex: Relies heavily on Tier 2 and Tier 3 vocabulary with limited contextual scaffolding. Often unfamiliar, archaic, subject-specific, and/or overly academic Often presents challenges that may slow down comprehension, but does not completely block the comprehension of the bulk of the text Exceedingly complex: Uses dense academic and domain-specific vocabulary that is likely to be inaccessible without significant support. Mostly unfamiliar, archaic, subject-specific, and/or overly academic May be ambiguous or purposefully misleading Makes comprehension of the bulk of the text very challenging and requires careful effort to interpret
Reasoning	Detailed explanation of the rating. Grades 3-4 reference density and cumulative effect, contextual scaffolding, abstract vs. concrete vocabulary, conceptual load, and the provided student background knowledge; other grades reference the annotation guide and rubric
Tier 2 words	Tier 2 words in the text — words commonly used in academic settings, more complex than colloquial or everyday language, often with multiple meanings
Tier 3 words	Tier 3 words in the text — overly academic or domain-specific words
Archaic words	Archaic words in the text — common words used in an archaic way, not commonly used in modern conversational language
Other complex words	All other words that can increase complexity of the text (e.g., idioms, unfamiliar proper nouns that function as vocabulary)

Evaluator release history

Date	Changed
August 27, 2026	Minor prompt updates
September 23, 2025	First release

Text Complexity evaluators

Explore other evaluators that assess qualitative text complexity.

Text Complexity dataset

Explore the expert-annotated benchmark behind Text Complexity evaluators.

Quickstart

Run an evaluator in the Evaluators playground, a Python notebook, or with the SDK.

Understanding evaluators

Getting started

SDK API reference

Text Complexity evaluators

Feedback evaluators

Academic standards evaluators

Durable skills evaluators

Datasets

Resources

Overview

At a glance

Getting started

Inputs

Output

Evaluator release history

Text Complexity evaluators

Text Complexity dataset

Quickstart

​Overview

​At a glance

​Getting started

​Inputs

​Output

​Evaluator release history

​Related topics

Text Complexity evaluators

Text Complexity dataset

Quickstart

Overview

At a glance

Getting started

Inputs

Output

Evaluator release history

Related topics