logoalt Hacker News

lanthissa • yesterday at 9:44 PM • 1 reply • view on HN

looks good gemini team fixed the massive spread they had vs openai and anthropic in terminal bench - swe bench.

That spread is my personal bs detector for models over promising.


Replies

andriy_koval • yesterday at 10:39 PM

I suspect all labs just benchmaxed those benches by now.