Tülu 3 405B is the largest model in the Tülu 3 family, applying fully open post-training recipes at a 405B parameter scale. Built on the Llama 3.1 405B base, it leverages Reinforcement Learning with Verifiable Rewards (RLVR) to enhance instruction following, MATH, GSM8K, and IFEval performance. As part of Tülu 3’s fully open-source approach, it offers state-of-the-art capabilities while surpassing prior open-weight models like Llama 3.1 405B Instruct and Nous Hermes 3 405B on multiple benchmarks. To read more, click here.(opens in new tab)