Verified80% confidenceFactTime unknown
HumanEval是由OpenAI于2021年发布的代码生成基准测试，包含164个手写的Python编程问题
15
Sources
80%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedHumanEval基准测试由OpenAI于2021年随Codex模型论文一同发布，包含164道编程题，Pass@1指一次生成即通过全部测试用例的比例82% similarUnverifiedHumanEval was developed in-house by OpenAI and is specifically designed to test the functional correctness rate of code generation.80% similarUnverifiedHumanEval tests code generation capabilities by requiring models to generate correct Python code based on function signatures and docstrings.74% similarUnverifiedHumanEval focuses on code generation capability, testing models' logical reasoning and code correctness with 164 programming problems.70% similarVerifiedThe HumanEval benchmark contains 164 programming problems and is the mainstream standard for measuring code generation capability.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/25134API
curl https://kongchang.com/api/v1/knowledge/claims/25134MCP
get_claim(id=25134)