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

It isn’t stronger for these sorts of reasoning tasks.


It is, according to the benchmarks. I'm just taking the materials they provided at face value.

If you have run your own benchmarks or have convincing anecdotes to the contrary, that would be an interesting contribution to the discussion.




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

Search: