A recent math test, known as First Proof, has been administered to artificial intelligence systems, with the results being mixed. Some outlets report that an OpenAI model was able to solve a famous math problem that had gone unsolved for decades, while others suggest that the overall performance of ai systems on the test was mediocre, with one assessment giving a grade of "C–". The test's outcomes have sparked interest in the capabilities and limitations of ai in solving complex math problems.