Grok 4.6 ties Claude Opus 5 for #1 on Artificial Analysis Agentic Index

elonmusk · x · 2026-08-21

Per Artificial Analysis, Grok 4.6 (High) scored 59 on the Agentic Index, tying Claude Opus 5 (Max) for first place and ahead of other leading models. The index focuses on real-world agentic capabilities: tool use, planning, autonomy, and complex problem-solving — significant as Grok expands into Grok Build and Grok Bot.

Related event: Grok 4.6 Ties Claude Opus 5 for Top Spot on Agentic Index(2 posts)→

Original post →

More from Models

Models channel →