NutriBench
DongXzz / UCSB
People ask assistants how many calories or carbohydrates are in a meal, and there is no easy way to check the replies. This is a benchmark of meal descriptions checked by people, with nutrition figures to score model estimates against.
QUICK INFO
SOLUTION TYPE
Models, data & tools
TECHNOLOGY CATEGORY
Benchmarks & evaluations
AREA OF WORK
Food safety, quality & nutrition
ACCESS
Free · Open source
DEPLOYMENT
Self-hosted / on-premise · Downloadable
SOURCE REVIEWED
August 17, 2026
What it helps with
- How many calories are in this meal
- Check if an assistant gets carbs right
- Test nutrition estimates from meal descriptions
- Compare models on calorie counting
- Carbohydrate figures for common meals
- Score a diet app against real numbers
Scope & audience
WHO IT'S FOR
Food safety & QA manager · Developer / AI builder
AREA OF WORK
Food safety, quality & nutrition
COMMODITY / SCOPE
Cross-commodity
Access & technical details
ACCESS
Anyone can get it
INTERFACE
Code repository · 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
MERA_Industrial evaluation harness
MERA-Evaluation, AI Alliance Russia
Models, data & tools
Before trusting an AI system on a farming or food task you need a way to check it. Runs the ruTXTAgroBench agronomy task on lm-evaluation-harness with fixed prompts and packs results for leaderboard submission.
Free · Open source
Self-hosted / on-premise · Downloadable
Benchmarks & evaluations
MERA_Industrial evaluation harness
research-develop
research-and-scientific-knowledge
buildable-or-downloadable-component
benchmarks-and-evals
Free · Open source
Self-hosted / on-premise · Downloadable
August 17, 2026
- Run the Russian agronomy test on my model
- Produce results ready for leaderboard submission
- Test a model with fixed prompts
- Score my model on farming questions
- Evaluation code for an agronomy benchmark
ARPA 1 qualification of safety systems providing obstacle detection and robot safety functions
INRAE, via agrifoodTEF
Services & solution providers
Before trusting an AI system on a farming or food task you need a way to check it. Tests whether an autonomous agricultural robot detects a reference obstacle and stops, using the protocol in ISO 18497:2024 Part 4 Annex D.2.
Paid or approval
Cloud-hosted
Benchmarks & evaluations
ARPA 1 qualification of safety systems providing obstacle detection and robot safety functions
research-develop
research-and-scientific-knowledge
obtainable-service-or-consultancy
benchmarks-and-evals
Paid or approval
Cloud-hosted
August 17, 2026
- Does my farm robot stop for an obstacle
- Test obstacle detection on an autonomous machine
- Qualify a robot safety function
- Run the standard obstacle stopping test
- Independent robot safety testing
Is this your Resource?
Contact us to claim this listing and add details, screenshots or a demo.