Cognition· Devin / SWEModel update

Cognition shared an early preview of its SWE-1.6 model, which achieves an 11% higher score than SWE-1.5 on SWE-Bench Pro. The company is rolling out early access to a small subset of users to collect feedback for tuning model behavior. The training stack has been improved to run 6x faster than three months ago.

From the source

We are sharing an early preview of our ongoing SWE-1.6 training run. Since training SWE 1.5, we have refined our RL recipe and scaled our infrastructure to unlock two orders of magnitude more compute. Our next model SWE-1.6 is post-trained on the same pre-trained model as SWE-1.5 and runs equally as fast at 950 tok/s. The current checkpoint achieves an 11% higher score than SWE-1.5 on SWE-Bench Pro. We are rolling out early access to this model to a small subset of users to collect feedback for tuning model behavior. Our goal for the preview period is to fix rough edges and further push intelligence as we continue training the model!

cognition.com