Or try SWE-1.6 in Windsurf today: https://windsurf.com/

Cognition released SWE-1.6, their latest software engineering model optimized for both intelligence and "model UX," now generally available in the Windsurf IDE. It is free for the next three months via a partnership with Fireworks at 200 tok/s, with a faster paid tier running at 950 tok/s through a partnership with Cerebras. SWE-1.6 was post-trained from scratch to jointly optimize for user experience and raw intelligence, achieving comparable benchmark performance to the Preview model while delivering dramatic improvements in behavioral smoothness, such as reduced overthinking, looping, and unnecessary tool use.

SWE-1.6 is lightning fast! Here's what 950 tok/s feels like - available in Windsurf today.
We’re releasing SWE-1.6, our best model in both intelligence & model UX. SWE-1.6 matches our Preview model on SWE-Bench Pro while dramatical…
SWE-1.6 is free for everyone in Windsurf for the next 3 months at 200 tok/s. For paying users, we've partnered with Cerebras to serve the mo…
With SWE-1.6 we've made significant progress on 'intelligence per token'. We post-trained the model from scratch (same pre-trained model) wi…
Ok @cognition SWE-1.6 Fast is better than expected. Had it built a quick prototype UI, looks better than what Figma Make generated and is ri…

Source: agents

Related