1w ago

OpenAI o3 beats FrontierMath — because OpenAI funded the test and had access to the questions

pivot-to-ai.com OpenAI o3 beats FrontierMath — because OpenAI funded the test and had access to the questions

OpenAI released its o3 model in December, bragging about the model’s unparalleled ability to do math and science problems. The model’s success on the FrontierMath benchmark — solving 25.2% of…

Fuck AI @lemmy.world

prototype_g2 @lemmy.ml

1w ago

OpenAI o3 beats FrontierMath — because OpenAI funded the test and had access to the questions

pivot-to-ai.com /2025/01/20/openai-o3-beats-frontiermath-because-openai-funded-the-test-and-had-access-to-questions/

69 2

6 comments

Besiroglu says OpenAI did have access to many of the FrontierMath problems and solutions — but he added “we have a verbal agreement that these materials will not be used in model training.”
It's not like the company building a plagiarism tool would use said tool to plagiarize training data. That would be inconceivable.