Add Qwen 2.5 72B benchmark result: 7.98/10

Add benchmark results for Command A, Gemma 3, and Llama 3.3

Remove Elm/STC from providers, add Eval method column (API vs HuggingFace)

Redesign leaderboard: fix dark mode, add ALLaM-7B results

Add results/nuha_llama-3.3-70b-versatile.json

Add README.md

Add requirements.txt

Add app.py

initial commit