Expired60% confidenceBenchmarkExact time
Modern code generation models have already achieved a one-pass success rate of over 90% on authoritative code benchmarks such as HumanEval.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/15/2026
First Seen
Valid until: 10/13/2026(expired)
Sources
Related Claims
VerifiedCode large language models are evaluated using executable benchmarks such as HumanEval and MBPP, meaning the generated code is directly executed and the output is checked for correctness.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% similarVerifiedHumanEval focuses on code generation capability, testing models' logical reasoning and code correctness with 164 programming problems.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% similarVerifiedHumanEval was developed in-house by OpenAI and is specifically designed to test the functional correctness rate of code generation.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/520777API
curl https://kongchang.com/api/v1/knowledge/claims/520777MCP
get_claim(id=520777)