Unverified50% confidenceFactExact time

SWE-Bench推出了SWE-Bench Verified和SWE-Bench Multimodal变体，前者人工筛选确保可解性，后者加入截图等多模态上下文

1

Sources

50%

Confidence

Long-term

Relevance

7/5/2026

First Seen

Sources

Grok CLI + Fish Audio 实战：零成本搭建全栈AI声音工作室

bilibilikate人不错7/2/2026

Related Claims

Unverified官方给出了针对Terminal Bench 2.1、SWE Bench Verified/Pro以及CLAW Eval等多个基准的评测数据73% similar VerifiedSWE-bench Verified经过人工审核确保每个实例的质量和可解性72% similar UnverifiedSWE-bench Verified由人工标注者筛除描述模糊或测试不稳定的样本，是业界权威的AI编程能力排行榜之一69% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/112517

API

curl https://kongchang.com/api/v1/knowledge/claims/112517

MCP

get_claim(id=112517)