Cognition Releases Coding Model SWE-2 Flash, Built on Inkling-Small
Cognition has released the fast coding model SWE-2 Flash, built on thinkymachines' Inkling-Small, with 276B total parameters and 12B activated parameters. The company claims it costs 5 times less and is 3 times faster than SWE-2, and surpasses all US open-weight models on major benchmarks, including models 3 times larger. The model will be free this month for Pro, Max, and Teams users of Devin Desktop and Devin CLI, and its weights will be released on a targeted basis through partner programs.
Why read this
SelectedAI score 68
The original text provides the base model, parameter scale, and cost and speed comparisons for SWE-2 Flash, which readers can use to assess the cost-effectiveness trajectory of small-parameter coding models.
Topics
Body
SWE-2 Flash is based on @thinkymachines Inkling-Small, an American model with 276B total and 12B active parameters. The small size, combined with our highly optimized inference stack allows us to offer it at a 5x lower cost and 3x higher speed than SWE-2. https://t.co/Se49qXj9sd