# Cognition Releases SWE-2 Coding Model Trained on Kimi K3

Digest AI · Generative AI & Models · published 2026-09-10T16:52:11Z · updated 2026-09-12T23:56:03Z

Canonical: https://digestai.news/story/cognition-s-swe-2-breaks-terminal-bench-2-1-with-92-8

## Summary

Cognition has launched SWE-2, its most advanced coding model to date, post-trained using reinforcement learning on Moonshot AI's 2.8-trillion-parameter open model, Kimi K3. The model achieves a 50.0% score on the FrontierCode 1.1 Main benchmark, placing it within one percentage point of Fable 5.1 while operating at a 64% lower cost. 

SWE-2 introduces selectable reasoning-effort levels (medium, high, and max) trained within a single reinforcement learning run using Pareto-informed cost penalties. Compared to its predecessor, SWE-1.7, the new model significantly reduces over-exploration, with the medium setting taking 58% fewer turns and costing 81% less on benchmarks. SWE-2 is not available as open weights or a standalone API; it is accessible exclusively through Cognition's Devin platform.

## Key points

- SWE-2 scores 50.0% on FrontierCode 1.1 Main, matching Fable 5.1 performance at a 64% lower cost.
- The model is post-trained via reinforcement learning from Moonshot AI's 2.8T-parameter Kimi K3 base.
- It is available exclusively within the Devin agent platform, with no standalone API or open weights.

## Why it matters

SWE-2 demonstrates that scaling reinforcement learning on top of massive open-weights models can yield frontier-class coding capabilities at a fraction of the cost of proprietary giants, shifting the economics of AI-assisted software engineering.

## Sources

1. [Cognition Releases SWE-2: A Kimi K3 Post-Trained Coding Model That Matches Fable 5.1 on FrontierCode at 64% Lower Cost](https://marktechpost.com/2026/09/12/cognition-releases-swe-2-a-kimi-k3-post-trained-coding-model-that-matches-fable-5-1-on-frontiercode-at-64-lower-cost) (MarkTechPost, 2026-09-12)
2. [Cognition's SWE-2 achieves 92.8 on Terminal-Bench 2.1](https://tokenstead.ai/models/swe-2) (tokenstead.ai, 2026-09-10)

## Cite

Digest AI, "Cognition Releases SWE-2 Coding Model Trained on Kimi K3", 10 September 2026, https://digestai.news/story/cognition-s-swe-2-breaks-terminal-bench-2-1-with-92-8

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/cognition-s-swe-2-breaks-terminal-bench-2-1-with-92-8.json