Unverified50% confidenceFactExact time
SAO团队选取了SWE-Bench Verified、BeyondAIME和IMOAnswerBench三个高难度基准进行验证
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/12/2026
First Seen
Valid until: 12/11/2026
Sources
Related Entities
Related Claims
UnverifiedSWE-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75% similarVerifiedSWE-bench Verified经过人工审核确保每个实例的质量和可解性70% similarUnverifiedSWE-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编程能力排行榜之一68% similarUnverified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66% similarUnverified智能体评估基准测试套件包括GAIA、AgentBench和SWE-bench66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/910348API
curl https://kongchang.com/api/v1/knowledge/claims/910348MCP
get_claim(id=910348)