OpenHands@OpenHandsDevWe collaborated with @MistralAI to release a new open coding agent LLM, Devstral. OpenHands+Devstral is 100% local 100% open, and is SOTA for the category on SWE-Bench Verified: 46.8% accuracy. We're one step closer to an expert AI coder on your computer. Let's gooo 🚀Opens with an observation
OpenHands@OpenHandsDevBig news for open models: @MiniMax_AI M2.5 is out and it’s an excellent+affordable coding model. It ranks 4th in our benchmarks, the first open model to beat Claude Sonnet. Only Claude Opus and GPT-5.2 Codex score higher. Details on scores and limited-time free access below 🧵Opens with an observation