Excited to see @DeepCogito unveil Cogito v2. This family of models is a major step towards AI systems that reason carefully, ground their answers, and are self-improving. Among the strongest open models in the world, this new version is a great milestone towards superintelligent AI systems. I’m proud to support @drishanarora and the exceptional Deep Cogito team.
Drishan Arora
Drishan Arora1.8. klo 01.02
Today, we are releasing 4 hybrid reasoning models of sizes 70B, 109B MoE, 405B, 671B MoE under open license. These are some of the strongest LLMs in the world, and serve as a proof of concept for a novel AI paradigm - iterative self-improvement (AI systems improving themselves). The largest 671B MoE model is amongst the strongest open models in the world. It matches/exceeds the performance of the latest DeepSeek v3 and DeepSeek R1 models both, and approaches closed frontier models like o3 and Claude 4 Opus.
33,74K