A closer look at OpenAI and DeepMind's claims on the autonomous performance of their models on the first batch of First Proof problems with the assistance of Gemini 3.1.
DeepMind and OpenAI autonomously tackle First…
A closer look at OpenAI and DeepMind's claims on the autonomous performance of their models on the first batch of First Proof problems with the assistance of Gemini 3.1.