Hacker News

points by Fergusonb 1 day ago | 0 comments

Interesting - at time of writing, Carbon is claimed to be #1 on AA, but AA has not updated yet.

Excited to try it, opus level benchmarks with their omniscience score and multimodality seems worth testing!

I don't trust AA scores after the last update to the index. Specially now that they are including private benchmarks that no one can test by themselves but only trust the entity doing them.

[–] Marha01 1 day ago

I don't like it much, but I understand. It's the only way to be objective. Models are trained and benchmaxxed on any popular public benchmarks.

[–] JacobAsmuth 1 day ago

You'd prefer public questions and answer sheets that anyone can train on?

[–] techmunky 1 day ago

i was wondering why the pareto line moved so much. i did not remember it being all openai models. good to know i dont need crazy pills yet.

[–] andriy_koval 1 day ago

we need to make semi-educated decisions to pick model somehow, and AA is the best what is available

[–] verdverm 1 day ago

AA just updated their intelligence index to v5

https://artificialanalysis.ai/articles/artificial-analysis-i...

https://news.ycombinator.com/item?id=50268868

https://theainewsreport.com/2026-10-28-artificial-analysis-i...

IMO it emphasizes the wrong things if we are interested in "intelligence"

[–] machiaweliczny 1 day ago

I think it's best ranking of models so far

[–] verdverm 1 day ago

yea, I probably agree, but I also do not find it represents real world use and performance

There are many more aspects which affect outcomes