Home
Sign Up
Sign In
V2EX = way to explore
V2EX 是一个关于分享和探索的地方
Sign Up Now
For Existing Member
Sign In
V2EX
›
SWE-Bench
7 月 9 日, OpenAI 主动承认用于代码评测的 SWE-Bench Pro 有约 30% 的任务有缺陷,导致分数失真,不再推荐它作为前沿模型的主要评测标准
前沿快讯 🗞
•
JoeJoeJoe
PRO
•
7 days ago
• Lastly replied by
paopjian
6
Grok4 和 O3 免费使用,哈哈
分享发现
•
idblife
•
Jul 25, 2025
• Lastly replied by
idblife
2
[Paper Reading]: SWE-Bench: Can Language Models Resolve Real-World Github Issues?
Python
•
wjMcat
•
Aug 15, 2024
About
·
Help
·
Advertise
·
Blog
·
API
·
FAQ
·
Solana
·
1126 Online
Highest 6679
·
Select Language
创意工作者们的社区
World is powered by solitude
VERSION: 3.9.8.5 · 16ms ·
UTC 23:05
·
PVG 07:05
·
LAX 16:05
·
JFK 19:05
♥ Do have faith in what you're doing.
❯