Verified65% confidenceFactTime unknown
Claude Code依托的Sonnet模型在HumanEval、SWE-bench等主流编程基准测试中持续领先
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026
Sources
Claude Code安装配置教程：与Cursor/TRAE对比及国内使用方案
bilibili代码指南
Related Entities
Related Claims
UnverifiedOpenAI的o系列模型、Anthropic的Claude 3.5 Sonnet在代码生成基准测试（如HumanEval、SWE-bench）上的得分已接近或超过人类程序员平均水平77% similarUnverified在Pillow库RGB转HSV精度Bug测试中，Claude Code使用Sonnet 4.6模型一次通过，逻辑清晰，获得满分76% similarVerifiedClaude模型在SWE-bench等编程能力基准测试中持续领先72% similarUnverified测试者提出最优工作流为Sonnet负责规划，Haiku子代理执行具体操作，最后Sonnet负责复查71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/17488API
curl https://kongchang.com/api/v1/knowledge/claims/17488MCP
get_claim(id=17488)