The tweet was deleted by the author.
But we saved everything 🙂.
Muse Spark 1.1 has achieved state-of-the-art results on the Radiologists Last Exam Handover Readiness Index (RadLE-H), according to Alexandr Wang. The artificial intelligence model's performance is now close to that of human experts in radiology, signaling notable progress in medical AI. The new benchmark underscores growing confidence in the deployment of AI tools to aid clinical decision-making while meeting rigorous standards for healthcare technology.
Alexandr Wang previously reported that Muse Spark 1.1 outperformed Opus, Grok 4.5, and Gemini on a theoretical computer science challenge. He also described Muse Spark 1.1 as one of the top-performing models for OpenClaw and HermesAgent applications. These developments follow ongoing advances in the AI model across different technical domains.