OpenGVLab/GenExam

GenExam: A Multidisciplinary Text-to-Image Exam

41
/ 100
Emerging

This project offers a specialized benchmark for evaluating text-to-image models on their ability to generate precise images based on complex, multidisciplinary instructions. It takes detailed text prompts across subjects like science, humanities, and arts as input, and outputs generated images which are then scored for semantic accuracy and visual plausibility. This is useful for AI researchers and developers working on or evaluating advanced image generation models.

Use this if you are developing or comparing text-to-image models and need a rigorous way to assess their precision in generating specific, exam-style visual content across various academic and professional domains.

Not ideal if you are looking for a tool to generate images for creative projects or general use, as this is a benchmark for evaluating model performance.

AI model evaluation generative AI text-to-image image synthesis multidisciplinary knowledge
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 8 / 25

How are scores calculated?

Stars

62

Forks

4

Language

Python

License

MIT

Last pushed

Feb 27, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/OpenGVLab/GenExam"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.