Overview
Cognition, the company behind the Devin coding agent, has released SWE-2, its most capable coding model to date. SWE-2 is post-trained with reinforcement learning from Kimi K3, Moonshot AI's 2.8T-parameter open model. Cognition reports a score of 50.0% on FrontierCode 1.1 Main, within 1 point of Fable 5.1 at 64% lower cost. It is also Cognition's first model with selectable reasoning-effort levels, all trained in a single RL run.
Deployment
SWE-2 is not deployable on your own infrastructure. It has no open weights and no standalone API. It runs only inside Devin: Desktop and CLI today, with Devin Web and Fusion rolling out.
What is SWE-2
SWE-2 builds on the infrastructure and recipe behind SWE-1.7, which was post-trained from Kimi K2.7. This time Cognition scaled RL to the multi-trillion-parameter regime, using a base model with almost 3x the parameters. Cognition says its RL still finds substantial headroom on top of K3, adding 5 to 6 points on many benchmarks.
The main change is an RL algorithm that trains all 3 effort levels in one run. Each level carries its own cost penalty, so the whole cost-and-performance frontier moves at once.
Benchmark Results
Cognition published the following table. Public results are used where available; otherwise each model runs in its native harness at best effort.
| Benchmark | SWE-2 | Kimi K3 | Grok 4.6 | Fable 5.1 | GPT-5.6 Sol | GPT-6 Astra | SWE-1.7 |
|---|---|---|---|---|---|---|---|
| FrontierCode 1.1 Main | 50.0% | 44.2% | 48.0% | 50.9% | 47.5% | 53.3% | 42.0% |
| DeepSWE 1.1 | 73.0% | 68.5% | 67.5% | 67.4% | โ | ||
Editor's note: The original article includes a full benchmark table; the excerpt above shows the first two rows. All technical terms and results are preserved as published.
via MarkTechPost