New Version Boosts Math Skills but Remains Incomprehensible

littmath · x · 2026-07-14

The poster believes that `5.6 Sol Pro/Ultra` shows a significant improvement in math capabilities over `5.5`. However, it also highlights a common interaction pattern: the model thinks for a long time and outputs a nearly incomprehensible answer; when the user asks for an explanation, it spends even more time before finally admitting its previous response was wrong.

Related event: New Model Boosts Math Power but Users Complain About Unreadable Output(2 posts)→

Original post →

More from Models

Models channel →