📌 📄 内容摘要:
Chetas (@chetaslua) 在 GPT-5xHigh is the new king of Reasoning 中发帖
CritPt is a research-level physics reasoning benchmark designed to test whether an AI can do genuine, expert-grade theoretical physics reasoning.
The highest score is 11.6% by GPT-5.2xHigh
[Screenshot 2026-01-06 at 12.11.55 PM]
────────── 链接信息 ──────────
🔗 论坛链接: linux.do
📎 访问地址: https://linux.do/t/topic/1411743/1
─────────────────────────────
📢 来源：LINUX DO
