Poolside AI Introduces Laguna XS.2 and M.1: Agentic Coding Models Reaching 68.2% and 72.5% on SWE-bench Verified

Poolside AI has launched Laguna M.1 and XS.2, advanced coding models with MoE architecture achieving up to 72.5% accuracy on SWE-bench Verified. These models offer efficient training methods like Muon optimizer and AutoMixer data optimization, making them valuable for developers seeking enhanced local machine performance and agentic coding capabilities.

Read the full article at MarkTechPost

---

Want to create content about this topic? Use Nemati AI tools to generate articles, social posts, and more.