Unverified50% confidenceBenchmarkExact time
MBPP包含974个基础Python任务,评估指标通常为pass@k
1
Sources
50%
Confidence
Long-term
Relevance
8/13/2026
First Seen
Sources
Related Claims
UnverifiedThe MBPP code generation benchmark contains approximately 500 Python programming problems targeting entry-level programmers.66% similarUnverifiedMBPP 全称为 Mostly Basic Python Problems,是一种考察模型独立封闭问题表现的代码基准62% similarVerifiedMBPP (Mostly Basic Python Problems) was released by Google and contains approximately 1,000 entry-level programming problems.61% similarUnverifiedLLM 库通过 Python 的 entry_points 机制实现插件系统,支持数千种不同模型的统一访问53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/741000API
curl https://kongchang.com/api/v1/knowledge/claims/741000MCP
get_claim(id=741000)