VibeBench: Measuring 1k Engineers' Opinions of New Models(vibebench.standardagents.ai)

12 ポイント投稿者 jpschroeder2 か月前4 コメント

https://vibebench.standardagents.ai/

4 コメント

ramon1562 か月前

Love the idea!

Page is incredibly slow on mobile, probably the avatars

800 commits in a year...

mhi32 か月前

"Published benchmarks are gamed, optimized, and overfit, and no longer yield a useful signal."

Is this true?

But I love this concept!

Oh very true. Benchmaxxing itself is basically gaming them.