MiniMax M2.1 was officially announced, scoring 72.5% on SWE-multilingual.

"A SOTA 10B-activated OSS coding & agent model, scoring 72.5% on SWE-multilingual and 88.6% on our newly open-sourced VIBE-bench" https://t.co/PTAUhvaT3a pic.twitter.com/s0EjiyHSqO

— 🚨 AI News | TestingCatalog (@testingcatalog) 23 décembre 2025

MiniMax M2.1 was officially announced, scoring 72.5% on SWE-multilingual. "A SOTA 10B-activated OSS coding & agent model, scoring 72.5% on SWE-multilingual and 88.6% on our newly open-sourced VIBE-bench"

→ View original post on X — @testingcatalog