SWE-2
Cognition · Released Sep 2026
SWE-2 is Cognition's coding model for Devin, post-trained from Kimi K3, and Cognition claims it lands within one point of Fable 5.1 on FrontierCode 1.1 Main at 64% lower cost. Conditional because every SWE-2 score is vendor-reported, the same table shows it far behind Fable 5.1 and GPT-6 Astra on Terminal-Bench 4, and it runs only inside Devin. Right for Devin Desktop and CLI users; wrong for anyone who needs an API model or independently verified results.
Is it right for you?
Good for
- Devin Desktop and Devin CLI users: SWE-2 has been available there since September 10, 2026, with Devin Web and Fusion rolling out
- Terminal-Bench 2.1-style tasks, where Cognition reports 92.8%, ahead of Fable 5.1 (91.4%) and GPT-6 Astra (89.9%) in the same table
- Picking an effort level per task: it ships as SWE-2 Medium, High and Max, which Devin's Enterprise SaaS model list bills at 6x, 9x and 12x credit multipliers, with High marked recommended
- Cost-sensitive agentic coding, if Cognition's claim holds: 50.0% on FrontierCode 1.1 Main, within one point of Fable 5.1 while being 64% cheaper, with costs assuming list pricing including public discounts
Not good for
- Terminal-Bench 4 workloads: Cognition's own table puts SWE-2 at 27.3%, against 55.8% for Fable 5.1 and 57.9% for GPT-6 Astra
- Anyone who needs an API or open weights: MarkTechPost reports no open weights and no standalone API, Devin only
- Buyers who need independent verification: every SWE-2 score comes from Cognition's post, which reports public results where they exist and otherwise evaluates each model in the harness it was primarily developed for
- Planning around context length, since Cognition's post publishes no context window
Pricing
Input
N/A (no standalone API)
Output
N/A (no standalone API)
Context
Devin only; Enterprise $0.75 in/$3.75 out per 1M
Benchmarks
No verdict changes yet
The clock starts day one. Changes land here as our verdict evolves.
Sources
Verification log
- Pricing· Needs attention
Automated agent
No per-token price on the Cognition post or the Devin models page, so the stored Enterprise $0.75/$3.75 rate stays unsourceable. Stored values kept.
- Pricing· Needs attention
Automated agent
Devin models page fetch returned a truncated cost table with no SWE-2 rows, and Cognition's SWE-2 post states no per-token price, so the stored Enterprise $0.75/$3.75 could not be sourced. Stored value kept.
- Pricing· No changes
Automated agent
- Pricing· No changes
Automated agent