Bergur Thormundsson
Research expert covering technology in the Nordics, AI and smart cities
Get in touch with us nowAs of March 2024, OpenAI o1 was the large language model (LLM) tool that had the best benchmark score in solving math problems, with a score of 94.8 percent. Close behind, in second place, was OpenAI o1-mini, followed by GPT-4o.
* For commercial use only
Basic Account
Starter Account
The statistic on this page is a Premium Statistic and is included in this account.
Professional Account
1 All prices do not include sales tax. The account requires an annual contract and will renew after one year to the regular list price.
Overview
North American focus
European focus
Attitudes towards AI use
Future of AI in healthcare
* For commercial use only
Basic Account
Starter Account
The statistic on this page is a Premium Statistic and is included in this account.
Professional Account
1 All prices do not include sales tax. The account requires an annual contract and will renew after one year to the regular list price.