Unverified50% confidenceBenchmarkExact time
斯坦福HAI研究所2023年报告显示，最新LLM在HumanEval等代码基准测试中正确率已超过85%，远超2021年的不足50%
1
Sources
50%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
VerifiedPass rates of code generation models on benchmarks such as HumanEval jumped from 60% to over 90% between 2024 and 202574% similarUnverified自2023年GPT-4发布以来，AI在HumanEval等主流编程基准测试上的通过率从不足50%跃升至90%以上73% similarUnverified斯坦福大学2023年的研究表明，主流AI检测工具误判率可高达20%以上72% similarUnverifiedThe pass rate of top models in 2025 on the HumanEval benchmark has exceeded 90%.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/541184API
curl https://kongchang.com/api/v1/knowledge/claims/541184MCP
get_claim(id=541184)