Devstral 2 is the new SOTA open-weight coding family, achieving 72.2% on SWE-bench Verified. It ships with Mistral Vibe, an open-source CLI agent for end-to-end code automation. Currently free via API.
Mistral just raised the bar for open-weight coding models. Devstral 2 (123B) hits 72.2% on SWE-bench Verified, effectively making it the new SOTA in the open-source space.
It rivals larger open models like DeepSeek V3.2 and gets surprisingly close to closed models like Claude Sonnet 4.5, but at a fraction of the inference cost. The smaller 24B version runs locally on consumer hardware but still punches above its weight.
They also released Mistral Vibe, a native CLI agent that handles end-to-end code automation right in your terminal.
Wow, Mistral AI looks amazing! The Devstral 2 SWE-bench score is incredible. How easily does Mistral Vibe integrate with existing CI/CD pipelines for automated testing?
It’s wild that a 7B model is beating Llama 13B on reasoning benchmarks. The sliding window attention seems to be doing a lot of heavy lifting here. Curious if anyone has tried fine-tuning this for specific RAG tasks yet? I am wondering how fragile the reasoning gets once you saturate the context window
Would anyone know about a cursor like alternative that could use such models running locally ? I know about Cursor + running model locally and using nGrok but I am looking for something a bit more solid here.
72.2% on SWE-bench is legit. Open-weight coding models being competitive with closed ones is huge for dev autonomy.
Q: How does the latency compare for real-time IDE integration? Also, is the VIbe CLI available now or just the model weights?
Shipping this matters! 🚀
Congratulations... finally something from Europe. I currently use Claude Code. How does it fare in terms of data protection (model training)? Now it just needs to work as well as Claude Code.
Upvoted. Impressive SWE-bench score. Quick question: how does Vibe handle safety/guardrails for write operations in real repos (e.g., limiting blast radius, requiring approvals), and do you publish latency/cost benchmarks for the 24B running on consumer hardware (RAM/VRAM footprint, tokens/sec)?
Yeah what should I say. It's another Mistral release within 1 week and I've tested it yesterday. Must admit that it's really good and the Devstrall Small is punching above it's weight. Works smooth on my M4 chip and can't complain yet 👌🏻
About Devstral 2 on Product Hunt
“SOTA open-source agentic coding models and CLI agent”
Devstral 2 launched on Product Hunt on December 10th, 2025 and earned 200 upvotes and 7 comments, placing #7 on the daily leaderboard. Devstral 2 is the new SOTA open-weight coding family, achieving 72.2% on SWE-bench Verified. It ships with Mistral Vibe, an open-source CLI agent for end-to-end code automation. Currently free via API.
Devstral 2 was featured in Open Source (68.3k followers), Artificial Intelligence (466.2k followers) and Development (5.8k followers) on Product Hunt. Together, these topics include over 100.7k products, making this a competitive space to launch in.
Who hunted Devstral 2?
Devstral 2 was hunted by Zac Zuo. 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 Devstral 2 stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Zac Zuo
Hi everyone!
Mistral just raised the bar for open-weight coding models. Devstral 2 (123B) hits 72.2% on SWE-bench Verified, effectively making it the new SOTA in the open-source space.
It rivals larger open models like DeepSeek V3.2 and gets surprisingly close to closed models like Claude Sonnet 4.5, but at a fraction of the inference cost. The smaller 24B version runs locally on consumer hardware but still punches above its weight.
They also released Mistral Vibe, a native CLI agent that handles end-to-end code automation right in your terminal.
The API is currently free to use!