llm-colosseum

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM (by aws-banjo)

llm-colosseum reviews and mentions

Posts with mentions or reviews of llm-colosseum. We have used some of these posts to build our list of alternatives and similar projects.
  • AWS open source newsletter, #194
    1 project | dev.to | 2 Apr 2024
    llm-colosseum is another repo that takes a more creative look at benchmarking your LLM's, this time using a classic video arcade fighting game. My colleague Banjo has put together this repo, together with a supporting blog post, 14 LLMs fought 314 Street Fighter matches. Here's who won, which is a must read this week. Check out the repo and post for videos of these LLMs playing games.

Stats

Basic llm-colosseum repo stats
1
41
9.4
about 1 month ago

aws-banjo/llm-colosseum is an open source project licensed under MIT License which is an OSI approved license.

The primary programming language of llm-colosseum is Jupyter Notebook.


Sponsored
SaaSHub - Software Alternatives and Reviews
SaaSHub helps you find the best software and product alternatives
www.saashub.com