Research
Cognition trains models optimized for software engineering. The challenge is not only improving raw capability, but also shaping agent behavior. Agents should feel fast, simple, and easy to course-correct. They should respond clearly, recover gracefully from mistakes, and remain steerable as tasks become more complex. Our focus is building models that are reliable in real workflows, not just impressive in isolated benchmarks.
Articles
Introducing SWE-2: Pushing the Pareto Frontier
09.10.26Today we’re introducing SWE-2, our most advanced coding model yet. SWE-2 delivers highly competitive agentic coding performance across multiple effort levels, pushing the Pareto frontier of capability and inference cost.
Factoring RSA-260
09.09.26How Devin and a Cognition researcher built the world’s highest-performance GPU lattice siever, to make factoring numbers 10x cheaper than the previous state of the art
SWE-1.7: Frontier Intelligence at a Fraction of the Cost
07.08.26Today, we’re launching SWE-1.7, the most capable model we’ve trained so far. It reaches frontier-level intelligence at a much lower cost, advancing the cost-performance Pareto curve.
Measuring the Trustworthiness of Open-Source-Derived Models
07.08.26We built an evaluation suite to assess model trustworthiness. Our results indicate that models developed from open-source models can be trusted, provided that sufficient thought and care is put into their development.
Join the Research Team
We’re a small team working on the hardest problems in AI. You’ll work with some of the best researchers and engineers in the field, pushing models to write better code, reason better, and work more autonomously. If this excites you, come build with us.