Unverified50% confidenceFactExact time
HumanEval通过让模型根据函数签名和文档字符串生成完整函数实现来衡量编码准确率
1
Sources
50%
Confidence
Long-term
Relevance
8/18/2026
First Seen
Sources
Related Claims
UnverifiedHumanEval tests code generation capabilities by requiring models to generate correct Python code based on function signatures and docstrings.77% similarUnverifiedHumanEval等传统代码评测基准通常只要求模型根据函数签名和文档字符串生成独立函数，本质上是受限的代码补全任务76% similarUnverifiedModel evaluations in the code generation field, such as HumanEval and SWE-bench, place special emphasis on functional correctness rather than fluency.74% similarUnverifiedCode 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.74% similarUnverifiedHumanEval focuses on code generation capability, testing models' logical reasoning and code correctness with 164 programming problems.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/771029API
curl https://kongchang.com/api/v1/knowledge/claims/771029MCP
get_claim(id=771029)