logoalt Hacker News

mkagenius • today at 6:07 AM • 1 reply • view on HN

> https://github.com/localixai/tokendoctor/tree/main/bench

Don't we need to run it on all of the benches those models publish?

This doesn't look very comprehensive. Moreover half of the times factory claude code is better than 'advised' one.

Although I don't discourage such experiments, I feel this one is way complicated for very little or no gain provably.


Replies

zshorastal • today at 7:05 AM

[flagged]