看到佬友们有判断 claude 是否降智的需求 分享一下这个网站
网址:
marginlab.ai
Claude Code Opus 4.7 Performance Tracker | Marginlab
Track Claude Code's daily performance on SWE-Bench-Pro. Monitor for degradation with statistical significance testing.
以下为 codex
marginlab.ai
Codex gpt-5.5-xhigh Performance Tracker | Marginlab
Track Codex's daily performance on SWE-Bench-Pro. Monitor for degradation with statistical significance testing.
7 个帖子 - 5 位参与者
来源: LinuxDo 最新话题查看原文