BREAKING : Grok 4 will be SOTA – 35% on HLE, 45% with reasoning
– 87-88% on GPQA – 72-75% on SWE Bench (for Grok 4 Code) * Not official benchmarks, I plotted these based on the leaked scores and results from the web for other models
Grok 4 SOTA avec des scores élevés
By
–
AGI AI AI HARDWARE APPS AUTOMATION BIG TECH CODE COMPUTING CREATIVE AI CULTURE DATA DECENTRALIZED AI ETHICS GENERATIVE AI HEALTHCARE AI INDUSTRY INNOVATION INVESTMENT JOBS LLMS MACHINE LEARNING MARKET TRENDS MULTIMODAL AI PROMPT ENGINEERING REGULATION RESEARCH ROBOTICS SAFETY SECURITY SOFTWARE STARTUPS SUSTAINABILITY SYSTEMS TOOLS WEB3 WORKFORCE