Reka

A model for robotics, beating models such as Cosmos-Reason2. Its noncommercial license converts into Apache 2.0 after two years.

Reka Flash 3 was a model overlooked by many. While the blog is sparse on details, they stick to RLOO with some DAPO-like modifications.

A 21B reasoning model, trained with RLOO and released under Apache 2.0. This is the first open weights release by Reka AI but it went under due to the release of Gemma shortly after. However, the model is really capable, especially for its size. In our testing, it came close to the performance of 32B models, such as the R1-distill of Qwen and QwQ 32B.