Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra
Cognition released SWE-2, a coding model post-trained from Kimi K3 that scores 50.0% on FrontierCode 1.1 Main, near Fable 5.1 at 64% lower cost.
Cognition introduced SWE-2, its most advanced coding model, post-trained from the 2.8T-parameter Kimi K3 base model. It achieves 50.0% on FrontierCode 1.1 Main, 73.0% on DeepSWE 1.1, and 92.8% on Terminal-Bench 2.1, beating Grok 4.6 and SWE-1.7 while matching Fable 5.1 and GPT-5.6 Sol at a fraction of the price. The company says it scaled reinforcement learning to the multi-trillion-parameter regime for the first time, using Pareto-informed cost penalties that train all reasoning-effort levels in a single run, tripled RL environments, and NVFP4/FP8 quantization-aware training. SWE-2 is available today in Devin Desktop and CLI, with rollout on Devin Web and Fusion.
- Scores 50.0% on FrontierCode 1.1 Main, within one point of Fable 5.1 at 64% lower cost
- Post-trained from Kimi K3, a 2.8T-parameter model, adding 5-6 points on many benchmarks
- Scaled RL to multi-trillion-parameter regime, training all reasoning-effort levels in one run
- SWE-2 medium takes 58% fewer turns and costs 81% less than SWE-1.7 on FrontierCode
- Available in Devin Desktop and CLI today, rolling out on Devin Web and Fusion
From the original article
13 min read at cognition.com
Today we’re introducing SWE-2, our most advanced coding model yet. It pushes the Pareto frontier of capability and cost, achieving 50. 0% on FrontierCode 1.
By seelos · cognition.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.