The article doesn't mention one of the most complex benchmarks - ARC challenge. ... | Hacker News

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

		godjan on April 12, 2025 \| parent \| context \| favorite \| on: Google is winning on every AI front The article doesn't mention one of the most complex benchmarks - ARC challenge. All models suck in it https://arcprize.org/leaderboard but Gemini and Claude still suck much worse then ChatGPT models

nolist_policy on April 12, 2025 [–]

They haven't tested Gemini 2.5 Pro yet.

usaar333 on April 12, 2025 | [–]

They have.

https://x.com/arcprize/status/1905361753678246308

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