Cognition's coding model that scores 50.0% on FrontierCode 1.1 Main at 64% lower cost than comparable frontier models.

SWE-2 works by combining Pareto-Frontier Cost Efficiency: Matches GPT-5.6 Sol and Fable 5/5.1 on coding benchmarks at a fraction of their price and comes within a few points of GPT-6 Astra at roughly a quarter of the cost., Single-Run Multi-Effort RL: A reinforcement learning algorithm trains all reasoning-effort levels in one run, applying a per-level linear cost penalty derived from the base model's local frontier slope., Focused Codebase Exploration: Stronger engineering judgment lets the model decide which parts of a repository matter, cutting mean steps per run from 127 to 53 at medium effort., Selectable Effort Levels: Ships medium, high and max reasoning settings so teams can trade additional steps and cost for accuracy on harder tasks., End-to-End Test Writing: Produces tests that validate an implementation end to end, catching regressions and edge cases more reliably than previous SWE models. to help users with Agentic Software Engineering: Powering Devin sessions that plan, edit, build and test changes across a real repository with minimal supervision., Cost-Sensitive Coding at Scale: Teams running large volumes of automated coding tasks pick a model that holds frontier-adjacent accuracy at a materially lower per-task cost., Terminal and Tooling Workflows: Strong Terminal-Bench results suit tasks driven through shell commands, build systems and command-line tooling., Regression Test Generation: Generating end-to-end tests for existing implementations to catch edge cases before a release., Effort-Tiered Task Routing: Routing simple tickets to medium effort and hard migrations to high or max effort within the same model deployment..

Key features include Pareto-Frontier Cost Efficiency: Matches GPT-5.6 Sol and Fable 5/5.1 on coding benchmarks at a fraction of their price and comes within a few points of GPT-6 Astra at roughly a quarter of the cost., Single-Run Multi-Effort RL: A reinforcement learning algorithm trains all reasoning-effort levels in one run, applying a per-level linear cost penalty derived from the base model's local frontier slope., Focused Codebase Exploration: Stronger engineering judgment lets the model decide which parts of a repository matter, cutting mean steps per run from 127 to 53 at medium effort., Selectable Effort Levels: Ships medium, high and max reasoning settings so teams can trade additional steps and cost for accuracy on harder tasks., End-to-End Test Writing: Produces tests that validate an implementation end to end, catching regressions and edge cases more reliably than previous SWE models..

SWE-2 is useful for anyone interested in Agentic Software Engineering: Powering Devin sessions that plan, edit, build and test changes across a real repository with minimal supervision., Cost-Sensitive Coding at Scale: Teams running large volumes of automated coding tasks pick a model that holds frontier-adjacent accuracy at a materially lower per-task cost., Terminal and Tooling Workflows: Strong Terminal-Bench results suit tasks driven through shell commands, build systems and command-line tooling., Regression Test Generation: Generating end-to-end tests for existing implementations to catch edge cases before a release., Effort-Tiered Task Routing: Routing simple tickets to medium effort and hard migrations to high or max effort within the same model deployment..

SWE-2 is a paid product. Check the official site for current pricing.

Visit https://cognition.com/blog/swe-2 to sign up and explore SWE-2.