c/fosai · by twelvefloatinghands@lemmy.world · 3y

Benchmark tracking for open-source models?

Just starting to look into open source AI models. Is anyone aware of anywhere with a table of all the open source models and their scores on various available benchmarks?

Edit: Found it: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard

9 points · 1 comments · view on lemmy.world

1 Comments

Blaed@lemmy.world · 2 pts · 3y

If you're looking to broaden your search, I've found a few more resources to share. Hope this helps!

LLM Leaderboards

HuggingFace Open LLM Leaderboard
LMSYS Chatbot Arena
LudwigStumpp's Leaderboard Repo

LLM Search Tools

LLM Explorer
Open LLMs

LLM Eval & Benchmark Resources

Holistic Evaluation of Language Models (HELM)
TextSynth
The Curious Case of LLM Evaluations
Mosaic Benchmarks

I'm going to add a few of these to the sidebar for quick access. Let me know if I've missed one!