AI is actually bad at math, ORCA shows

go.theregister.com/feed/www.theregister.com/2025/11/17/ai_bad_math_orca

ORCA 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.…

This story appeared on go.theregister.com, 2025-11-17 21:16:24.
The Entire Business World on a Single Page. Free to Use →