OpenAI Secretly Funded Benchmarking Dataset Linked To o3 Model
Revelations that OpenAI secretly funded and had access to the FrontierMath benchmarking dataset are raising concerns about whether it was used to train its reasoning o3 AI reasoning model, and the validity of the model’s high scores. In addition to accessing the benchmarking dataset, OpenAI funded its creation, a fact that was withheld from the … Read more