GIFT Eval

GIFT Eval

The Salesforce page for GIFT-Eval, a benchmark for general time series forecasting. Its repository holds a results folder and the app code. Suits forecasting researchers and ML engineers comparing models.

Made by Salesforce on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This Space is the home of GIFT-Eval, Salesforce's benchmark for judging how well models predict time series. Time series forecasting means predicting future values of a measured series. The repository holds a results folder next to the app, so the page appears to present benchmark results, though the README says little beyond the title.

Who it suits: It suits researchers and ML engineers who build or choose forecasting models and want a shared benchmark, and students who want to see how forecasting models are compared.

Industry | Who uses it | How they use it | Example
Research | Forecasting researchers | Look at benchmark results for models | Check where a model family stands
Machine learning | ML engineers | Choose a forecasting model by its benchmark showing | Compare candidate models before picking one
Education | Students | Learn how forecasting models are evaluated | Read the benchmark's results page
Software | Developers | Read an app that reports benchmark results | Open app.py and the src folder

You can skip it if you need a tool that forecasts your own data, since this page is about a benchmark.

Where to use it:

• A web browser: open the Space page on Hugging Face
• Windows, macOS or Linux: run a copy with Python 3.10.0

Use case | Who | What they get back
Browse results | Researchers | The benchmark's published results
Compare models | ML engineers | A view of how forecasting models score
Run your own copy | Developers | The same app on your own computer

How to set it up: The online page needs nothing. A local copy needs Python 3.10.0 and the packages in requirements.txt.

• A web browser for the online page
• Python 3.10.0 for a local copy
• The packages listed in requirements.txt

1. To use it online, open the Space page on Hugging Face.
2. To run a copy, install the Hugging Face hub package.
3. Download the Space into a local folder.
4. Move into the folder and install Gradio 4.44.0 and the listed packages.
5. Start the app.

pip install -U huggingface_hub
hf download Salesforce/GIFT-Eval --repo-type space --local-dir GIFT-Eval
cd GIFT-Eval
pip install gradio==4.44.0
pip install -r requirements.txt
python app.py

How to use it: Start the app from its folder, or open the Space online, then read what the page shows. The README gives no usage notes, so look through the page and the results folder to see what is listed.

python app.py

Example: You open the page to see how forecasting models compare on the benchmark. You note the models that score well and then look at the repository's results folder for the underlying files.

For newcomers and experts: If you are new to this, forecasting is the task of estimating future values from past ones, such as sales next week. Start by browsing the page and reading what a benchmark result looks like.

If you know the field, the repository holds a results folder, a source folder and a small build setup with a Makefile and pre-commit config. The hosted Space runs on Hugging Face's basic CPU hardware and uses an older Gradio release.

The benchmark's results are stored in the repository
The app reads them
You browse them on the page

Good to know: The release is for research only, to support an academic paper. It is not evaluated for every downstream use, so check accuracy, safety and fairness before relying on it. Salesforce asks users to follow its acceptable use policies, particularly in high-risk settings.

• License: apache-2
• Cost to run: none named
• Data it reaches: the benchmark results stored in the repository
• Not for: high-risk uses without your own checks, since it is a research release

On Hugging Face, 13 November 2026

• Likes: 253
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/Salesforce/GIFT-Eval
• Files: https://huggingface.co/spaces/Salesforce/GIFT-Eval/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.