๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

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.
๊ฐ€์ž… March 2020
73 ํŒ”๋กœ์ž‰ ์ค‘    2.8K ํŒฌ
Over 142 continuous hours in building Wave 2 of my newest eval suite. A lot was done in this wave. For those just jumping in. I'm building the suite in parallel in Factory and Claude Code, comparing what each comes up with and using the best of both to finalize the full suite. This will be the first eval suite from VulcanBench all on the @harborframework, something I am very excited to be moving to. More to come ๐Ÿ––
๋” ๋ณด๊ธฐ