Since the leaderboard was created, a lot of cool initiatives emerged, let's centralize them here!
Thanks so much to the community 🤗

Discussions around the leaderboard

• What is going on with the Open LLM Leaderboard? is a discussion on the different existing ways to do evaluation: blog, discussion.

Community initiatives

• @danielpark created a visualization report repository using the stats of the open LLM Leaderboard, website, discussion.
• @CoreyMorris created a leaderboard for detailed MMLU results: space, discussion
• @gregzem created a huge queryiable table of extended model information: website , discussion
• @felixz created up to date summaries of the current best models: here and a way to download leaderboard data easily here
• @Weyaxi created a tool to extract and convert leaderboard data to your format of choice (csv, html, json): website, discussion
• @Weyaxi also created an amazing tool to help you if you need to rename your model: use this which will automatically open PRs on the results dataset of your file, and link them all in a discussion!

Hugging Face leaderboards

• Multilingual code evaluations by @loubnabnl
• Human and GPT4 evaluation by @nazneen and @natolambert
• Performance benchmarks by @IlyasMoutawwakil

Resources about LLMs

• LocalLLMComparisions: repository to compare the performance of small LLMs (pointed out by @zmcmcc )
• AlpacaEval Leaderboard
• MT Bench

Feel free to comment with your own initiatives and spaces!