VulcanBench(@VulcanBench):I am going to be dedicating some time to a new eval suite. We need more benchmarks exploring new ways to measure model safety. As a truly independent benchmark, made by me, just one guy, who has never worked at an AI lab in my life, I feel I can bring a unique perspective. Coming soon 🖖

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.

参加 March 2020

63 フォロー中 2.3K ファン

VulcanBench@VulcanBench

2026.09.13 04:32

I am going to be dedicating some time to a new eval suite. We need more benchmarks exploring new ways to measure model safety. As a truly independent benchmark, made by me, just one guy, who has never worked at an AI lab in my life, I feel I can bring a unique perspective. Coming soon 🖖