Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

It's around Qwen-3.8, and Sonnet 5.5 level, but a lot cheaper. It is also really fast.

My tests for Haiku 5.5: https://aibenchy.com/compare/anthropic-claude-haiku-5-5-xhig...

Twice as expensive as Luna, but also considerably smarter too:

https://aibenchy.com/compare/anthropic-claude-haiku-5-5-xhig...



A really big difference can be seen in this basic CSS animation generation of a solar system of Luna vs Haiku:

https://aibenchy.com/compare/anthropic-claude-haiku-5-5-xhig...


not a great comparison.

haiku x-high: Cost $0.028, Tokens 54,579

luna high: Cost $0.004 Tokens 6,679


Sort of, it is still the model's job to know how much it should reason for a job to do be done properly.


Sure but Luna didn't correctly do the orbit paths. On Firefox Mobile (at least), the Luna version they're all sharing the same path.


Yeah, that was my point to OP's comment.

Luna was faster and cheaper, but the output didn't work.


Their entire benchmark is deeply flawed and every model release they astroturf it (and I appear to call that out, but only after someone else independently verifies that it's bunk)




Consider applying for YC's Winter 2027 batch! Applications are open till November 2.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: