AI is actually bad at math, ORCA shows

by
from The Register on (#71HMZ)
Story ImageORCA benchmark trips up ChatGPT-5, Gemini 2.5 Flash, Claude Sonnet 4.5, Grok 4, and DeepSeek V3.2

In the world of George Orwell's 1984, two and two make five. And large language models are not much better at math....

External Content
Source RSS or Atom Feed
Feed Location http://www.theregister.co.uk/headlines.atom
Feed Title The Register
Feed Link https://www.theregister.com/
Feed Copyright Copyright © 2025, Situation Publishing
Reply 0 comments