Unverified50% confidenceBenchmarkExact time
现代代码生成模型已能在HumanEval等权威代码基准测试上取得超过90%的一次性通过率
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/15/2026
First Seen
Valid until: 10/13/2026
Sources
Related Claims
Unverified通过知识与代码流程的显式映射，代码生成的准确率可以提升到90%以上75% similarUnverified代码大语言模型采用HumanEval、MBPP等可执行基准评估，即直接运行生成代码并检验输出是否正确68% similarUnverified传统代码评测基准（如HumanEval、MBPP）主要测试模型在孤立函数级别的生成准确率67% similarUnverifiedHumanEval专注代码生成能力，以164道编程题检验模型的逻辑推理与代码正确性65% similarUnverifiedHuman-in-the-Loop架构中系统通常自动处理高置信度文档（约占总量的70%-90%），将低置信度文档路由给人工审核65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/520777API
curl https://kongchang.com/api/v1/knowledge/claims/520777MCP
get_claim(id=520777)