AgriMM benchmark
Boudiaf et al. (academic release)
Testing whether a model really understands crop photographs needs more than a handful of examples. This is a downloadable collection of farm images paired with questions and answers, gathered from many existing datasets, plus scoring scripts.
QUICK INFO
SOLUTION TYPE
Models, data & tools
TECHNOLOGY CATEGORY
Benchmarks & evaluations
AREA OF WORK
Crop protection & plant health
ACCESS
Free · Open source
DEPLOYMENT
Self-hosted / on-premise · Downloadable
SOURCE REVIEWED
August 23, 2026
What it helps with
- Test if a model understands crop photographs
- Farm images paired with questions and answers
- Compare models on tomato and grape photos
- Score a crop photo assistant
- Test set for farm image questions
Scope & audience
WHO IT'S FOR
Developer / AI builder · Scientist / researcher
AREA OF WORK
Crop protection & plant health
COMMODITY / SCOPE
Tomato · Wine grape · Specialty & horticulture · Cross-commodity
Access & technical details
ACCESS
Anyone can get it
INTERFACE
Dataset download
DEPLOYMENT
You run it yourself
LANGUAGES
Not stated by provider
Featured media
Source information
This listing was compiled from publicly available source material. Verify current details with the provider.
PROVIDER DOCUMENTATION
Reviewed August 2026
Explore more like this
GEOBench-VLM
The AI Alliance
Models, data & tools
Before trusting an AI system on a farming or food task you need a way to check it. 31 geospatial vision-language tasks with over 10,000 verified instructions, including crop type classification and farm pond change detection.
Free · Open source
Self-hosted / on-premise · Downloadable
Benchmarks & evaluations
GEOBench-VLM
research-develop
research-and-scientific-knowledge
buildable-or-downloadable-component
benchmarks-and-evals
Free · Open source
Self-hosted / on-premise · Downloadable
August 17, 2026
- Test a vision language model on satellite tasks
- Classify crop type from satellite images
- Detect changes in farm ponds
- Compare models on geospatial instructions
- Verified instruction set for earth imagery
Leaf Segmentation Challenge (LSC), Codabench edition
CVPPP 2017 organisers
Models, data & tools
Before trusting an AI system on a farming or food task you need a way to check it. Segments every individual leaf in plant images, scored with BestDice, symmetric best Dice and foreground-background Dice.
Free
Cloud-hosted
Benchmarks & evaluations
Leaf Segmentation Challenge (LSC), Codabench edition
research-develop
research-and-scientific-knowledge
buildable-or-downloadable-component
benchmarks-and-evals
Free
Cloud-hosted
August 17, 2026
- Count individual leaves in a plant photo
- Outline every leaf separately
- Test a leaf segmentation model
- Compare leaf outlining accuracy
- Benchmark for individual plant leaf images
Is this your Resource?
Contact us to claim this listing and add details, screenshots or a demo.