Unverified60% confidenceBenchmarkExact time
HumanEval, MBPP, and SWE-bench are standard benchmark datasets specifically targeting code generation.
2
Sources
60%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
VerifiedMainstream benchmarks for evaluating programming large models include HumanEval, MBPP, SWE-bench, and LiveCodeBench81% similarUnverifiedHumanEval、SWE-bench等代码评测基准的排名是评估执行型Agent底层模型选型的重要参考维度79% similarVerifiedCode 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.76% similarUnverifiedHumanEval and MBPP primarily evaluate single-function-level code generation and have relatively limited discriminating power for agent-type tools.75% 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75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/535381API
curl https://kongchang.com/api/v1/knowledge/claims/535381MCP
get_claim(id=535381)