# SWE-1.7 14 Hacker News commenters recommended SWE-1.7 and 20 criticized it, November 2025 to November 2026. It was recommended in 4 of 13 months. **Verdict:** Recommended as a fast, low-cost coding model that comes close to frontier performance on price. Most common caveat: benchmark claims are self-reported and it only works inside Cognition's own harness. ## Why people recommend it - Good quality for the price (3 comments): "I bought the 20$ subscription and have been using SWE-2 for a few days now, and it's actually good." ([source](https://news.ycombinator.com/item?id=49723949)) "a model from a smaller lab can beat weeks-old Fable 5.1 at 70% lower cost" ([source](https://news.ycombinator.com/item?id=49649930)) "great that we have a new leader in performance/price in that segment" ([source](https://news.ycombinator.com/item?id=49650070)) - Impressive technical achievement (2 comments): "This is an excellent write up of an excellent technical achievement." ([source](https://news.ycombinator.com/item?id=48835141)) "It's seriously quite impressive." ([source](https://news.ycombinator.com/item?id=49662072)) - Improving with each release (3 comments): "windsurf swe-1 is good enough for my use case and swe-1.5 is even better" ([source](https://news.ycombinator.com/item?id=46509129)) "the models did get better but yeah their early product was godawful" ([source](https://news.ycombinator.com/item?id=49647094)) "SWE-1.5 was surprisingly good when I used it last." ([source](https://news.ycombinator.com/item?id=49646140)) ## What people warn about - Benchmarks self-reported or unverified (4 comments): "A company whose first demo was completely fraudulent announces that its model beats GPT-5.5, on its own benchmark?" ([source](https://news.ycombinator.com/item?id=48834110)) "on their own benchmark that they made, that they ran themselves in their own closed-source ecosystem" ([source](https://news.ycombinator.com/item?id=49649332)) "Seems like benchmaxing? For example for Terminal-Bench 4 it doesn't have great results." ([source](https://news.ycombinator.com/item?id=49646136)) - Only usable in its own harness (4 comments): "Would have been worth a consideration if it could have been used beyond it's own harness." ([source](https://news.ycombinator.com/item?id=48834880)) "I'm disappointed to see I need to use a bespoke platform to interact with this agent" ([source](https://news.ycombinator.com/item?id=49646173)) "they all have desktop apps and have a plan, how do i use SWE-2?" ([source](https://news.ycombinator.com/item?id=49647438)) - Trails rival models in practice (4 comments): "1.7 was unusable for me. Took more time thinking than GLM 5.2 and seemed to be generally running in circles." ([source](https://news.ycombinator.com/item?id=49646612)) "I'm not using yet another tool and subscription for a model that isn't even winning." ([source](https://news.ycombinator.com/item?id=48834936)) "The model also seems worse in every way than DeepSeek v4.1 Flash, launched today." ([source](https://news.ycombinator.com/item?id=49646233)) - Uses up paid quota quickly (2 comments): "took 14% of my daily quota in one prompt on the $20 plan" ([source](https://news.ycombinator.com/item?id=48836985)) "it doesn't appear to be free, it used up some of my on demand usage" ([source](https://news.ycombinator.com/item?id=49647379)) ## Alternatives hackers recommend - [Cursor Composer](https://hackerapproved.com/p/composer-2-5.md): 214 recommend - [Qwen3-Coder](https://hackerapproved.com/p/qwen3-coder-next.md): 165 recommend - [GPT-5.3-Codex](https://hackerapproved.com/p/gpt-5-3-codex.md): 135 recommend - [Meta Muse Glimmer 30B](https://hackerapproved.com/p/meta-muse-glimmer.md): 70 recommend - [GPT-5.2-Codex](https://hackerapproved.com/p/gpt-5-2-codex.md): 54 recommend ## Cite as Hacker Approved, "SWE-1.7", https://hackerapproved.com/p/swe-1-7/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).