Cognition SWE-2.

specs at a glance

how good is Cognition SWE-2 at coding?

Cognition SWE-2 is on our board but deliberately unranked. We rank by SWE-bench Verified, Cognition has not published that number, and no independent evaluation has run it, so there is nothing here we could stand behind. It moves into the ranking the moment a confirmed score exists.

Score provenance: Released Sept 10, 2026. Cognition's own numbers, all on benchmarks Cognition built or controls (FrontierCode 1.1 Main, DeepSWE 1.1, Terminal-Bench 2.1/4), not SWE-bench Verified: FrontierCode 1.1 Main 50.0% (vs SWE-1.7's 42.0%, Fable 5.1's 50.9%, GPT-6 Astra's 53.3%), DeepSWE 1.1 73.0%, Terminal-Bench 2.1 92.8%. Cognition claims an 81% average cost cut vs SWE-1.7 (58% fewer steps: 53 vs 127 on medium effort) and a 64% cost cut vs Fable 5.1 for a score within one point of it.

No SWE-bench Verified score published by Cognition or measured independently, and no token pricing or context window disclosed. Complicating factor: vals.ai archived its SWE-bench Verified board on Sept 5, 2026 citing score saturation, so this model may not get an independent score on our tracked metric at all. Enters the verifying queue unranked. Re-checked 2026-09-11: vals.ai's board remains archived (no new models being scored) and still shows no evaluation for this model.

See /p/cognition-swe-2-coding-model-launch/.

where can you use it?

Available via Devin Desktop · Devin CLI · Devin Web · Devin Fusion. As a proprietary model, you're on the maker's infrastructure and release schedule.

More coverageAI coding models on GENZ TECH

Ranked on our AI Coding Leaderboard — scores confirmed against primary sources only, updated 2026-09-03.