The Register on MSN

AI models still suck at math

Just less than before, according to the ORCA test exclusive Current-day LLMs are prediction engines and, as such, they can ...
AI could soon spew out hundreds of mathematical proofs that look "right" but contain hidden flaws, or proofs so complex we can't verify them. How will we know if they're right?
Tao: Today there are a lot of very tedious types of mathematics that we don’t like doing, so we look for clever ways to get ...
Add Yahoo as a preferred source to see more of our stories on Google. The ACT math test consists of 60 multiple-choice questions that must be completed in 60 minutes. A portion of those questions ...
OpenAI’s unreleased model solved five of 10 unpublished research-level math problems and proposed a breakthrough physics formula, signaling a new era for AI in science.
Mathematical modelling and optimisation in packing problems constitute a critical research area that combines advanced algorithms, rigorous analytical formulations, and practical applications. This ...
DeepSeek released DeepSeek-Math-V2, an AI model specialized for mathematical reasoning, on November 27, 2025. DeepSeek-Math-V2 focuses on theorem proving and self-verification capabilities, and ...
There are, generally speaking, two types of people in the mathematical optimization software field: • Optimization solver developers: The technical experts who devise and implement the algorithms that ...
The ACT math test consists of 60 multiple-choice questions that must be completed in 60 minutes. A portion of those questions involves modeling, which is the process of expressing real-life phenomena ...