[태그:] AI benchmarks

Meta Muse Spark just scored 52 on the Artificial Analysis Intelligence Index v4.0, placing it in the top 5 overall behind GPT-5.4 (57), Gemini 3.1 Pro (57), and Claude Opus 4.6 (53). That makes it the most capable AI model Meta has ever built, and it is completely free to use. Built by Meta Superintelligence […]

Google released Gemini 3.1 Pro on February 19, 2026, and its benchmark numbers are hard to ignore. The model scored 77.1% on ARC-AGI-2, a test specifically designed to prevent AI from relying on memorised answers — it forces genuine reasoning on problems the model has never encountered before. That is more than double the 31.1% […]

Today, November 17, 2025, xAI has officially rolled out Grok 4.1, the latest iteration of its flagship large language model, across grok.com, the 𝕏 interface, and the iOS and Android apps. The update arrives after a two-week silent production test and aims to deliver more natural conversation, stronger emotional intelligence, tighter safety controls, and dramatically improved real-world reliability. Unlike […]