Unverified50% confidenceFactExact time
MBPP 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
1
Sources
50%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
Claude Sonnet 4重回Cursor:CursorBench登顶,成本最高如何抉择
twittercursor_ai7/1/2026
Related Claims
VerifiedMBPP(Mostly Basic Python Problems)由Google发布,包含约1,000个入门级编程问题79% similarUnverifiedMBPP代码生成基准测试包含约500道面向初级程序员的Python编程题73% similarUnverifiedMBPP包含974个基础Python任务,评估指标通常为pass@k62% similarUnverified该项目的Python脚本handle_issue.py接收四个参数:仓库名、Issue编号、标题和正文,并自动创建分支名为claude-issue-{编号}61% similarUnverifiedPython因其简洁的语法和丰富的测试生态系统,已成为测试开发的首选编程语言59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/483559API
curl https://kongchang.com/api/v1/knowledge/claims/483559MCP
get_claim(id=483559)