Cognition releases SWE-1.5, a coding agent model served at up to 950 tok/s
Original titleIntroducing SWE-1.5: Our Fast Agent Model
Cognition has released SWE-1.5, a model optimized for software engineering that it says reaches near-frontier coding performance while running at up to 950 tok/s with Cerebras inference.
The company reports it is 6x faster than Haiku 4.5 and 13x faster than Sonnet 4.5, and it is available now in Windsurf.
The post's SWE-Bench Pro chart places SWE-1.5 at 40.08%, behind Sonnet 4.5 at 43.60%, and it notes that the model was trained with reinforcement learning on the Cascade agent harness.
The post pairs a benchmark chart with a 950 tok/s speed claim and describes how harness, RL environments, and inference were co-designed, useful context for judging the speed-versus-quality tradeoff.
Source: Cognition Blog (Devin, Windsurf) · cognition.com