News for hackers. Stuff that matters.
Re:Advancing the price-performance frontier with GPT‑5.6 by efficax on Thursday July 30, 2026 @02:45PM (#49114003)
is it? i don't know how we measure these things, but here's one measurement that says v4 pro is better than luna: https://artificialanalysis.ai/models/comparisons/gpt-5-6-lun...

presumably it's a much bigger model

Re:Advancing the price-performance frontier with GPT‑5.6 by energy123 on Thursday July 30, 2026 @02:57PM (#49114161)
This has already been updated with the new prices?
Re:Advancing the price-performance frontier with GPT‑5.6 by pornel on Thursday July 30, 2026 @03:53PM (#49114900)
The intelligence scores are absolute, not per $.

DeepSeek Pro is more capable than Luna regardless of the cost.

Re:Advancing the price-performance frontier with GPT‑5.6 by energy123 on Friday July 31, 2026 @12:25AM (#49118992)
There's also a cost graph on the same page and the context of this conversation is cost vs performance frontier.
Re:Advancing the price-performance frontier with GPT‑5.6 by lemming on Thursday July 30, 2026 @11:41PM (#49118744)
That’s comparing Luna on medium thinking with Deepseek on max. If you switch Luna to xhigh in that comparison it’s considerably more capable while still also cheaper.
Re:Advancing the price-performance frontier with GPT‑5.6 by jmolinski on Thursday July 30, 2026 @11:55PM (#49118819)
You are comparing Luna medium to Deepseek Max, when you switch to Luna high it's cheaper per task than DS and has a better intelligence score, which goes higher yet on xhigh and max reasoning levels.

https://artificialanalysis.ai/models/comparisons/gpt-5-6-lun...