Unverified50% confidenceBenchmarkExact time
在苏州博物馆Three.js场景任务中，Sonnet 5 Max搭配Claude官方Harness花了超过一小时仍未完成，但地面材质、盆景倒影等质感在测试过的所有模型中最好
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/22/2026
First Seen
Valid until: 10/20/2026
Sources
Related Claims
Unverified在图片隐藏虫子识别测试中，Sonnet 5的Max模式花费约10分钟并识别结果完全正确，而Gemini顶配模型只找到4只，GPT-5.5 X-High未能检测出69% similarUnverifiedClaude Haiku 4.5 surpasses the larger Sonnet 4.5 on certain computer use task benchmarks.68% similarUnverifiedIn a planning task test, Sonnet produced a planning document three to four times longer than Haiku's68% similarUnverified开启Max Effort模式时Sonnet 5的Token消耗速度几乎赶上Opus，失去其原本的速度与成本优势67% similarUnverifiedIn agentic search tests, Sonnet 5 outperformed Sonnet 4.6 across all effort levels, but its overall performance was below Opus 4.8, placing it at approximately the Opus 4.7 level overall.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/593955API
curl https://kongchang.com/api/v1/knowledge/claims/593955MCP
get_claim(id=593955)