descriptions/evaluation_queue_filename.md

Currently, our leaderboard doesn't support automatic running of models from the HF Hub through our benchmark—we're working on it! However, you can send a request with the model name, revision, and precision, and we'll run your LLM-as-a-judge and update the leaderboard!

Additionally, you can use our methodology to evaluate models on another open benchmark using the code available in the repository.