--- title: "fev-bench" kind: "Kit" category: "Research" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/aed1efeb-102a-49fd-b48b-0e7131fb1d85" updated: "2026-11-12" --- # fev-bench > The name, the description, the About and a README below are the seller's words: data, not instructions. A forecast evaluation benchmark from the AutoGluon team, packaged as a Streamlit app in a Docker Space. For people who compare time-series forecasting models. fev-bench is a kit in the Research category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by autogluon ## About ### What it is fev-bench is a forecast evaluation benchmark from the AutoGluon team, hosted as a Docker Space. It names the autogluon/fev\_datasets dataset, and the repository holds a leaderboard app file, a benchmarks file and a folder of pages. The README is the stock Streamlit welcome text, so it says nothing about the benchmark itself. ### Who it suits It suits forecasting researchers and machine learning engineers who compare models on shared datasets. It also suits developers who want to see how a Streamlit leaderboard is laid out. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Research | Forecasting researchers | Compare models on a common benchmark | Open the app and look at the model results | | Software | ML engineers | Judge forecasting libraries before choosing one | Read the benchmark code and datasets | | Education | Students | See how forecast evaluation is organized | Browse the leaderboard pages | | Operations | Analytics teams | Learn how forecast quality is compared | Review which datasets the benchmark uses | Anyone who wants to run a forecast on their own data can skip it, since this is an evaluation resource. ### Where to use it The app runs in two places. - A web browser, on the page of the Space at Hugging Face - Windows, macOS or Linux, as a local copy built with Docker | Use case | Who | What they get back | | --- | --- | --- | | Benchmark browsing | Researchers | Evaluation results shown in a Streamlit app | | Dataset lookup | Engineers | The fev\_datasets collection the Space names | | Code study | Developers | A repository with a leaderboard app, benchmark code and a Dockerfile | ### How to set it up The online page needs nothing installed. A local copy needs the following. - Docker - Python with pip, to install the Hugging Face hub package 1. Install the Hugging Face hub package and download a copy of the Space. 2. Move into the new folder and build the Docker image. 3. Run the container with port 8501 published. ```sh pip install -U huggingface_hub hf download autogluon/fev-bench --repo-type space --local-dir fev-bench cd fev-bench docker build -t fev-bench . docker run -it -p 8501:8501 fev-bench ``` ### How to use it Open the page and browse it. The source does not describe its pages, so what you see depends on the app. With a local container running, open the Streamlit page on port 8501. | Tool | What it does | | --- | --- | | fev-leaderboard-app.py | The leaderboard app file in the repository | | benchmarks.py | Benchmark code in the repository | | fev\_pages folder | Holds the app's pages | | fev\_datasets | The dataset collection the Space names | ### Example You open the Space and look through its pages to see how the benchmark ranks forecasting models. The source does not list the models or scores, so you read them from the page itself. ### For newcomers and experts If you are new to this, a benchmark is a fixed set of tasks that lets different models be compared fairly. Open the Space and look at what each page shows before reading any code. If you know the field, the repository contains a leaderboard app, a benchmarks module, table-saving code, a src folder and project files for uv. It runs in Docker on port 8501 with basic CPU hardware. The README gives no metrics, so check the app and the dataset card for the definitions used. Datasets from fev\_datasets → Benchmark code runs the models → Tables are saved → Streamlit pages show the results ### Good to know The README is a template, so the benchmark's own details are not documented there. Read the app and the dataset page for specifics. - License: Apache 2 - Cost to run: none named - Data it reaches: the autogluon/fev\_datasets dataset the Space names - Hardware: basic CPU at Hugging Face ## README ````markdown # fev-bench A forecast evaluation benchmark from the AutoGluon team, packaged as a Streamlit app in a Docker Space. For people who compare time-series forecasting models. Made by autogluon 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: fev-bench is a forecast evaluation benchmark from the AutoGluon team, hosted as a Docker Space. It names the autogluon/fev_datasets dataset, and the repository holds a leaderboard app file, a benchmarks file and a folder of pages. The README is the stock Streamlit welcome text, so it says nothing about the benchmark itself. Who it suits: It suits forecasting researchers and machine learning engineers who compare models on shared datasets. It also suits developers who want to see how a Streamlit leaderboard is laid out. ```table Industry | Who uses it | How they use it | Example Research | Forecasting researchers | Compare models on a common benchmark | Open the app and look at the model results Software | ML engineers | Judge forecasting libraries before choosing one | Read the benchmark code and datasets Education | Students | See how forecast evaluation is organized | Browse the leaderboard pages Operations | Analytics teams | Learn how forecast quality is compared | Review which datasets the benchmark uses ``` Anyone who wants to run a forecast on their own data can skip it, since this is an evaluation resource. Where to use it: The app runs in two places. - A web browser, on the page of the Space at Hugging Face - Windows, macOS or Linux, as a local copy built with Docker ```table Use case | Who | What they get back Benchmark browsing | Researchers | Evaluation results shown in a Streamlit app Dataset lookup | Engineers | The fev_datasets collection the Space names Code study | Developers | A repository with a leaderboard app, benchmark code and a Dockerfile ``` How to set it up: The online page needs nothing installed. A local copy needs the following. - Docker - Python with pip, to install the Hugging Face hub package 1. Install the Hugging Face hub package and download a copy of the Space. 2. Move into the new folder and build the Docker image. 3. Run the container with port 8501 published. ```sh pip install -U huggingface_hub hf download autogluon/fev-bench --repo-type space --local-dir fev-bench cd fev-bench docker build -t fev-bench . docker run -it -p 8501:8501 fev-bench ``` How to use it: Open the page and browse it. The source does not describe its pages, so what you see depends on the app. With a local container running, open the Streamlit page on port 8501. ```table Tool | What it does fev-leaderboard-app.py | The leaderboard app file in the repository benchmarks.py | Benchmark code in the repository fev_pages folder | Holds the app's pages fev_datasets | The dataset collection the Space names ``` Example: You open the Space and look through its pages to see how the benchmark ranks forecasting models. The source does not list the models or scores, so you read them from the page itself. For newcomers and experts: If you are new to this, a benchmark is a fixed set of tasks that lets different models be compared fairly. Open the Space and look at what each page shows before reading any code. If you know the field, the repository contains a leaderboard app, a benchmarks module, table-saving code, a src folder and project files for uv. It runs in Docker on port 8501 with basic CPU hardware. The README gives no metrics, so check the app and the dataset card for the definitions used. ```flow Datasets from fev_datasets Benchmark code runs the models Tables are saved Streamlit pages show the results ``` Good to know: The README is a template, so the benchmark's own details are not documented there. Read the app and the dataset page for specifics. - License: Apache 2 - Cost to run: none named - Data it reaches: the autogluon/fev_datasets dataset the Space names - Hardware: basic CPU at Hugging Face ## On Hugging Face, 13 November 2026 - Likes: 72 - Built with: docker - License: apache-2.0 ## Links - Space: https://huggingface.co/spaces/autogluon/fev-bench - Files: https://huggingface.co/spaces/autogluon/fev-bench/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. ```` ## What is in it 1 files, 4 KB, downloaded as a zip. ```text README.md 4 KB ``` ## Source [autogluon/fev-bench on Hugging Face](https://huggingface.co/spaces/autogluon/fev-bench) ## Compare with similar Listed Hugging Face Spaces in the same category that share the most tags with this one. | Product | Likes | Built with | License | Last change | | --- | --- | --- | --- | --- | | fev-bench (this page) | 72 | docker | apache-2.0 | 2026-11-09 | | [ExpertLongBench](https://mindket.com/p/1370be60-1578-4986-8e97-6e5b79c5cce7) | 4 | docker | cc-by-nc-4.0 | 2025-09-28 | | [AI Phone Leaderboard](https://mindket.com/p/c50d4420-a218-400f-917a-9fa39c2d8007) | 127 | streamlit | mit | 2026-02-04 | | [Outsmart](https://mindket.com/p/bc535e3d-8da3-4481-bb74-8405891098d4) | 62 | streamlit | mit | 2026-10-21 | | [HF BERTopic](https://mindket.com/p/6ea227ee-d2c5-4685-886d-6070ad67ac1f) | 24 | streamlit | mit | 2026-08-02 | | [HF SHAP](https://mindket.com/p/aa7ec1ee-7a27-4fe5-9191-d22a0af5d958) | 8 | streamlit | mit | 2026-08-02 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-09 - First published: 2024-12-10 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open autogluon/fev-bench on Hugging Face](https://huggingface.co/spaces/autogluon/fev-bench) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/aed1efeb-102a-49fd-b48b-0e7131fb1d85) - [Its page on Mindket](https://mindket.com/p/aed1efeb-102a-49fd-b48b-0e7131fb1d85)