SWE-2 is Cognition's new coding model, post-trained from Kimi K3 with RL that optimizes for cost and capability at the same time. It hits 50.0% on FrontierCode 1.1 Main, within a point of Fable 5.1 at 64% less, and lands within a few points of GPT-6 Astra at a quarter of the cost. Compared to SWE-1.7 it takes 58% fewer turns and costs 81% less while scoring higher. Available now in Devin Desktop and CLI.
Considering Cognition's SWE-2? Explore rivals like Claude for strong reasoning, Claude Code for deep-context repo work, Cursor for an agentic IDE, Codex 3.0 by OpenAI for autopilot build-test-debug, and Kilo Code for open-source control.