Unverified50% confidenceOpinionExact time
Grok 4.5 是第一个在 Three.js 等框架中3D建模能力几乎像样的模型，作者认为其效果超过 Fable 和 GPT-5.6
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/10/2026
First Seen
Valid until: 10/8/2026
Sources
Grok 4.5深度实测：编程能力媲美顶级模型，成本仅零头
youtubeTheo - t3․gg7/9/2026
Related Claims
UnverifiedGrok 4.5生成的Minecraft克隆版在所有顶尖模型中排名第三，前两名分别是Fable 5和GPT 5.574% similarUnverifiedGrok 4.5采用稠密模型架构，与GPT-4等采用的MoE稀疏架构不同，稠密模型每次推理都会激活全部参数71% similarUnverifiedAI aggregator platforms support access to models including GPT 5.5 Thinking, Grok 4.2, Claude 4.7, Gemini 3.1 Pro, and DeepSeek V4.67% similarUnverifiedGrok 4在MATH、HumanEval、MMLU等权威基准测试中表现突出，尤其在数学推理和代码生成领域与GPT-4o、Claude 3.5等顶级模型形成竞争66% similarUnverifiedGrok Build的UI风格与早期GPT 5.5高度相似，大量使用圆角设计元素，测试者推测可能存在训练数据'风格泄漏'66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/429550API
curl https://kongchang.com/api/v1/knowledge/claims/429550MCP
get_claim(id=429550)