AI models reach 75% on undergraduate FrontierMath

7.6 significance by International AI Safety Report Capabilities December 2030

Why does it matter?

Reaching 75% on hard math would make expert-level reasoning less exceptional for frontier systems.

Direct quote

In a study by the Forecasting Research Institute, experts forecast a 50% chance that AI models will achieve 55% accuracy by 2027 and 75% accuracy by 2030 on undergraduate-level FrontierMath problems.

International AI Safety Report