WHAT NEW IN X10.29 THU

AI collections from X · 22 collections · 60,636 posts

minimax-m3.1POST

Blogger suspects MiniMax M3.1 Flash of benchmark memorization

A blogger says MiniMax M3.1 Flash answers benchmark questions instantly but cannot name its own boss, suspecting the model memorized test sets rather than showing real ability.

Leo · Building w/ AI
@leo114119Archived 8 days agoOriginally posted 2026.10.20
Leo · Building w/ AI @leo114119Originally posted 2026.10.20
Open original on X

又一个博主质疑MiniMax m3.1 Flash 公开背题。。。。 题库里的题目秒答对,却不知道自已的老板是谁。。。。 MiniMax 还是不应该去刷分的。。。 实打实的进步,用户看得出来,免费一段时间口碑还是会起来的。。。。

This post quotes another post: “Suspicion that Minimax M3.1 Flash benchmaxxed AA Omniscience, passing Gemini 4 Argon”

x.com/leo114119/status/2112370180328431955Archived 2026.10.20 20:24