VulcanBench
@VulcanBench
Benchmarking models across effort levels and harnesses on eval suites with real coding tasks. Because you don't need High or Max effort as much as you think.
Joined March 2020
73 Following 2.8K Followers
Our analysis of Muse Wonder at Low and Medium efforts is now live in the new Analysis section on the site.
Trying to go further into analyzing traces and looking at how models think.
Hope you like it, and would love feedback đ
Show more
