SWE-2 is Cognition's new coding model, post-trained from Kimi K3 with RL that optimizes for cost and capability at the same time. It hits 50.0% on FrontierCode 1.1 Main, within a point of Fable 5.1 at 64% less, and lands within a few points of GPT-6 Astra at a quarter of the cost. Compared to SWE-1.7 it takes 58% fewer turns and costs 81% less while scoring higher. Available now in Devin Desktop and CLI.
SWE-2 is Cognition's new coding model, built to sit near the frontier without frontier pricing.
The problem: coding agents get smarter by getting more expensive, and often by burning tokens. Their own SWE-1.7 had this issue, users said it over-explored simple tasks.
What they did: post-trained Kimi K3 with RL that puts the actual dollar cost of a run into the training reward, and trains all three effort levels (medium, high, max) in one go instead of stitching separate models together. So the whole cost-performance curve moves up, not just the top end.
The numbers:
50.0% on FrontierCode 1.1 Main, within a point of Fable 5.1 at 64% less cost
Within a few points of GPT-6 Astra at a quarter of the price
92.8% on Terminal-Bench 2.1, top of their comparison table
vs SWE-1.7: 58% fewer turns, 81% cheaper, higher score. First code edit after 18 steps instead of 48
Also worth noting: better end-to-end test writing, and it re-derives conclusions when you push back instead of just agreeing with you.
Good fit if you're running coding agents at volume and per-task cost is an actual line item. Available now in Devin Desktop and CLI, rolling out to Web and Fusion.
The "58% fewer turns" number is the one I'd want to see stress-tested outside the benchmark suite - fewer turns to first working edit is great on a curated eval, but real repos have messier context (legacy code, half-documented internal APIs) where a model that reasons less per step can also just get stuck earlier and need a human to unstick it. Any word on how it holds up on messier, less benchmark-shaped codebases?
About Cognition's SWE-2 on Product Hunt
“Cognition's coding model, 64% cheaper than Fable 5.1”
Cognition's SWE-2 launched on Product Hunt on September 13th, 2026 and earned 189 upvotes and 3 comments, earning #3 Product of the Day. SWE-2 is Cognition's new coding model, post-trained from Kimi K3 with RL that optimizes for cost and capability at the same time. It hits 50.0% on FrontierCode 1.1 Main, within a point of Fable 5.1 at 64% less, and lands within a few points of GPT-6 Astra at a quarter of the cost. Compared to SWE-1.7 it takes 58% fewer turns and costs 81% less while scoring higher. Available now in Devin Desktop and CLI.
Cognition's SWE-2 was featured in Artificial Intelligence (478.9k followers) on Product Hunt. Together, these topics include over 122.1k products, making this a competitive space to launch in.
Who hunted Cognition's SWE-2?
Cognition's SWE-2 was hunted by Rohan Chaubey. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Cognition's SWE-2 stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Rohan Chaubey
SWE-2 is Cognition's new coding model, built to sit near the frontier without frontier pricing.
The problem: coding agents get smarter by getting more expensive, and often by burning tokens. Their own SWE-1.7 had this issue, users said it over-explored simple tasks.
What they did: post-trained Kimi K3 with RL that puts the actual dollar cost of a run into the training reward, and trains all three effort levels (medium, high, max) in one go instead of stitching separate models together. So the whole cost-performance curve moves up, not just the top end.
The numbers:
50.0% on FrontierCode 1.1 Main, within a point of Fable 5.1 at 64% less cost
Within a few points of GPT-6 Astra at a quarter of the price
92.8% on Terminal-Bench 2.1, top of their comparison table
vs SWE-1.7: 58% fewer turns, 81% cheaper, higher score. First code edit after 18 steps instead of 48
Also worth noting: better end-to-end test writing, and it re-derives conclusions when you push back instead of just agreeing with you.
Good fit if you're running coding agents at volume and per-task cost is an actual line item. Available now in Devin Desktop and CLI, rolling out to Web and Fusion.
Try it: the SWE-2 writeup
P.S. I hunt the latest and greatest launches in tech, SaaS and AI, follow to be notified → @rohanrecommends