LLM Leaderboards
By Xavier Collantes
It is hard to keep up with LLMs because major advancements happen weekly. These
leaderboards help me track the latest models and their performance against each
other.
LLM advancements are so fast, these leaderboards may not work or are migrated to another form.
HuggingFace Performance Leaderboard
Compares pricing, context window, pricing, and response time. This one I have
seen the most commonly referred to.
MTEB Leaderboard
This leaderboard compares 100+ text and image embedding models across 1000+
languages. Great for finding many human languages.
LLM Arena
Great for ranking use-specific LLMs: Text, Image, Vision, Search, Text-to-Image.
LLM Stats
Nice visual graph of LLM benchmarks. Contains the cutoff dates for training.
Vellum
Latest public benchmark performance for SOTA model versions released after April 2024. The data comes from model providers as well as independently run
evaluations by Vellum or the open-source community.
Related Articles
Related by topics:
ai
llm
rag