Show HN: I made 14 LLMs fight each other in 314 Street Fighter III matches(community.aws)
community.aws
Show HN: I made 14 LLMs fight each other in 314 Street Fighter III matches
https://community.aws/content/2dbNlQiqKvUtTBV15mHBqivckmo/14-llms-fought-314-street-fighter-matches-here-s-who-won
2 comments
its interesting it would say "Jump Cancel," which i gather wasn't an allowed move from the prompt, but which is an advanced SF/fighting game technique.
This was quite a fun project to create an actual chat bot arena, and gives rise to a new type of benchmark. Claude models were the top performing especially haiku