Unverified50% confidenceBenchmarkExact time
在Artificial Analysis智能指数中Grok 4.7（超高思考强度）排第五位得分46，前四名为Fable 5.1、Astra、Cloud Opus 5和MuseSpark 1.3 Max
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/25/2026
First Seen
Valid until: 10/9/2026(expired)
Sources
Related Entities
Related Claims
Unverified在 Artificial Analysis 榜单中，Step 5 预览版的智能分数达到 44 分，超过约 2.8 万亿参数的 Kimi K3 和 GLM，仅次于 Astra 与 Opus 576% similarUnverified在作者自制的代码审查基准中，Astra位居榜首，Grok 4.7紧随其后，Fable 5.1只提5条建议但质量很高73% similarPartially VerifiedMiMo V2.6 Pro在Artificial Analysis综合智能榜上拿下46分，与Grok 4.7并列第六、第七位70% similarUnverifiedGLM-5.3-Flash在Artificial Analysis综合智能指数评测中取得57分，与Claude Opus 4.8持平70% similarUnverifiedArtificial Analysis 给 Qwen 3.8 打出52的智能指数，追平满推理档的 GPT-5.6，智能体分51，高于 Claude Opus 4.869% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/949439API
curl https://kongchang.com/api/v1/knowledge/claims/949439MCP
get_claim(id=949439)