Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra

Cognition has launched its new SWE-2 model, which demonstrates strong performance in coding benchmarks, rivaling models like Fable 5.1 and GPT-Astra. The SWE-2 model achieved 50.0% on Main 50.0 %, 73.0% on DeepSWE 1.1, 92.8% on Terminal-Bench 2.1, and 27.3% on Terminal-Bench 4. Cognition also shared that it uses a length-weighted reward baseline, introduced since SWE-1.6, to stabilize training and reduce gradient variance.

This report is the first to detail Cognition's SWE-2 model, which outperforms SWE-1.7 across all listed benchmarks and introduces a new reward baseline.