Grok 4.6 Ties GPT-5.6 in Intelligence, Beats Claude Opus 5 in Agentic Efficiency

The Decoder · rss · 2026-08-13

xAI's Grok 4.6 scores 61 points on the Artificial Analysis Intelligence Index, tying OpenAI's GPT-5.6 Sol and trailing only Anthropic's Claude Opus 5.

For agentic tasks, Grok 4.6 demonstrates high efficiency, completing complex workflows in approximately 53 steps compared to Claude Opus 5's 103 steps. Additionally, it is priced at more than 60% lower than its competitors.

Original post →

More from Models

Models channel →