Support coding tasks
SWE-2 is Cognition’s coding model.
Coding / product dossier
Cognition's SWE-2
A coding model in Devin Desktop and CLI optimized for lower cost and fewer turns.
Product brief
What Cognition's SWE-2 does.
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.
Why we selected it
A technically specific coding-model release that targets both capability and operating cost, available in desktop and CLI workflows.
- Best for
- Cost-conscious AI coding teams
- Category
- Coding
- Daily picks
- 1
- First selected
- 2026-09-13
Product preview saved with our daily selection
Capability scan
What it can help with.
Only capabilities supported by the product information we collected are listed here.
Use post-training optimized for cost and capability
The model is post-trained from Kimi K3 with reinforcement learning intended to optimize cost and capability together.
Operate in Devin workflows
SWE-2 is available in Devin Desktop and CLI.
Reduce turns versus SWE-1.7
The description reports that SWE-2 takes 58% fewer turns than SWE-1.7 while scoring higher.
Best-fit use cases
Use a coding model in Devin Desktop.
Run coding-model workflows through the Devin CLI.
Evaluate a coding model when operating cost and task-turn count are important considerations.
Compare SWE-2’s reported FrontierCode 1.1 Main result with the named alternative models.
FAQ
Before you open it.
What is SWE-2?
SWE-2 is Cognition’s coding model, post-trained from Kimi K3 with reinforcement learning.
Where is SWE-2 available?
It is available in Devin Desktop and CLI.
What benchmark result is reported for SWE-2?
The description reports a 50.0% result on FrontierCode 1.1 Main.
How does SWE-2 compare with SWE-1.7?
The description reports 58% fewer turns, 81% lower cost, and a higher score than SWE-1.7.
What cost comparisons are stated for SWE-2?
The description states that SWE-2 is 64% less expensive than Fable 5.1 and costs one quarter as much as GPT-6 Astra.