Expired60% confidenceBenchmarkExact time
xAI的Grok 4.6在Artificial Analysis智能指数（Intelligence Index）中获得61分
2
Sources
60%
Confidence
Short-term (~14 days)
Relevance
8/14/2026
First Seen
Valid until: 8/28/2026(expired)
Sources
Related Claims
UnverifiedArtificial Analysis has launched a new agent benchmark, AA-Analyst Agent, focused on real-world quantitative analysis of spreadsheets and documents; in the leaderboard, Opus 5 leads with 54%, followed by GPT-5.5 and Fable 5.67% similarUnverifiedData from the Artificial Intelligence Index, published annually by Stanford University's Human-Centered Artificial Intelligence institute (HAI), shows that open-source models have caught up with the performance of closed-source models.63% similarUnverifiedRepresentative AI observability tools include LangSmith, Weights & Biases, Arize AI, and Phoenix.63% similarUnverifiedSWE-bench Verified has become the new standard for measuring AI Agent programming capability, with top Agent systems already surpassing a 50% solve rate.63% similarUnverifiedHIX AI's AI image generation feature supports output at up to 4K resolution.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/746813API
curl https://kongchang.com/api/v1/knowledge/claims/746813MCP
get_claim(id=746813)