Jun 17, 202610 items
A 3B dense model lands AIME26 at 94.3 and claims parity with flagship reasoners, while OpenAI ships a method to preview model behavior before deployment.
1 digest tagged coding-agents clear
A 3B dense model lands AIME26 at 94.3 and claims parity with flagship reasoners, while OpenAI ships a method to preview model behavior before deployment.