UGI Leaderboard

UGI Leaderboard

Shows a leaderboard of AI models scored on what its title calls Uncensored General Intelligence, as a page that runs in the browser or in Docker. For people comparing models.

Made by DontPlanToEnd 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: UGI Leaderboard is a web page that ranks AI models under the title Uncensored General Intelligence Leaderboard. Its data sits in CSV files inside the repository. You can open it online or build and run your own copy with Docker.

Who it suits: It suits people who compare AI models and want a ranking to check before choosing one to try.

Industry | Who uses it | How they use it | Example
AI research | Researchers | Look up how models compare on this leaderboard | Open the page and find a model you follow
Software | Developers | Narrow down which models to test | Compare a few models you are considering
Hobbyist AI | Enthusiasts | Keep track of new models | Return to the page to see what changed
Data work | Analysts | Read the raw numbers behind the page | Open the CSV files in the repository

Skip it if you need to know how the scores are made, since the source does not explain the method.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• Docker on your own Windows, macOS or Linux computer

Use case | Who | What they get back
Check a model's standing | Researchers | Its place on the leaderboard
Shortlist models | Developers | A ranked view to start from
Read the data | Analysts | The leaderboard's CSV files

How to set it up: The online page needs nothing. A local copy needs Docker, and Python with pip to fetch the files.

• Docker
• Python and pip, to fetch the files
• Windows, macOS or Linux

1. Install the Hugging Face hub library.
2. Download the Space's files into a folder named UGI-Leaderboard.
3. Move into that folder.
4. Build the Docker image.
5. Run the container with port 8050 published, then open that port in your browser.

pip install -U huggingface_hub
hf download DontPlanToEnd/UGI-Leaderboard --repo-type space --local-dir UGI-Leaderboard
cd UGI-Leaderboard
docker build -t ugi-leaderboard .
docker run -it -p 8050:8050 ugi-leaderboard

How to use it: Open the Space's page, or start the container with the last command above and browse to port 8050 on your machine. Then look through the leaderboard.

docker run -it -p 8050:8050 ugi-leaderboard

Example: You open the page and look for a model you are thinking of trying. You compare where it sits against the others on the leaderboard before deciding.

For newcomers and experts: Open the online page and scroll through it. That is all you need to do, and nothing has to be installed.

The app is built with Docker, serves on port 8050, and has app.py as its main file. The Hugging Face copy runs on the cpu-basic tier. The repository holds two CSV data files, one of them named as an old leaderboard, along with ideologies.js, an Images folder and an assets folder. The record gives no README text, so the scoring method is something you would read in the code and data.

Docker builds the image
The container runs app.py
The page is served on port 8050
You browse the leaderboard

Good to know:

• Hardware: The Hugging Face copy runs on the cpu-basic tier.
• Gaps: The source has no README text, so the scoring method and columns are not described here.
• License: apache-2.
• Cost to run: none named.
• Data it reaches: The CSV files in the repository. A local run also builds a Docker image and installs the packages in requirements.txt.

On Hugging Face, 13 November 2026

• Likes: 2,199
• Built with: docker
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard
• Files: https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard/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.