Unverified50% confidenceFactExact time
SWE-bench和GAIA是更接近真实世界的评测方法,SWE-bench基于真实GitHub issue修复,GAIA需要多步工具使用
1
Sources
50%
Confidence
Long-term
Relevance
8/27/2026
First Seen
Sources
Related Entities
Related Claims
Cite This Claim
Stable URI
https://kongchang.com/claim/807981API
curl https://kongchang.com/api/v1/knowledge/claims/807981MCP
get_claim(id=807981)