GradeLab vs Lettria

GradeLab is an assessment platform built for schools, universities, coaching centers, and government exam bodies that need to grade handwritten and digital exams faster without giving up teacher control. Upload scanned answer sheets or run online tests, and the system applies your rubrics to score essays, math, diagrams, and mixed-format papers while flagging anything that needs a human review.

What sets it apart is the focus on real exam workflows: OCR trained on student handwriting across 30+ languages, on-screen marking for distributed examiners, question generation from PDFs, LaTeX exam paper formatting, and REST APIs for LMS and EdTech integrations. Institutions can deploy on-premise so exam data stays inside their network.

GradeLab targets K-12 schools, higher-ed departments, test-prep centers, corporate training teams, and public-sector assessment programs that process large paper volumes and want consistent grading with analytics parents and administrators can actually read.

Lettria builds a graph context layer that turns enterprise documents and databases into ontology-backed knowledge graphs for automation teams. Its Knowledge Studio GraphRAG product parses PDFs, tables, SAP exports, and scanned annexes, then answers multi-hop questions with source citations. Perseus is the developer platform for generating ontologies and graphs without hand-modeling every entity.

Vector RAG tools retrieve similar chunks; Lettria follows explicit relationships across structured and unstructured data. The company publishes benchmark comparisons showing graph agents at 81.7% overall accuracy versus 57.5% for vector agents, plus text-to-graph claims of 30% higher accuracy and up to 400x faster extraction than general LLMs. That trade-off favors regulated teams that need audit trails over quick semantic search.

Finance, healthcare, legal, and engineering groups use Lettria for ESG filings, biomedical literature, contract corpora, and technical manuals. Case studies cite Alfa Laval (+30% extraction accuracy), AP-HP (+60% faster research), and Wisecube processing 108 GB of biomedical text into 500+ monitored classes.