All Topics
All Topics
Technology
Technology
Design
Design
Programming
Programming
Science
Science
News
News
Gaming
Gaming
Entertainment
Entertainment
Business
Business
Finance
Finance
Sports
Sports
Health
Health
Food
Food
Travel
Travel
Art
Art
Music
Music
Books
Books
Education
Education
Politics
Politics
Personal
Personal
No algorithm. No AI slop. No ads. Just RSS. Pro-human. Indie writers. Real journalism. Open web. Chronological. Hand toasted.

MiniMax Launches M2.5 AI Model with Enhanced Performance in Coding and Real-World Tasks

By

denysvitali

3mo ago· 11 min readen

Summary

MiniMax introduces its latest AI model, M2.5, which has been extensively trained with reinforcement learning in complex real-world environments. The model achieves state-of-the-art performance in coding, agentic tool use, search, office work, and other economically valuable tasks. It demonstrates significant improvements in benchmark scores including 80.2% in SWE-Bench Verified, 51.3% in Multi-SWE-Bench, and 76.3% in BrowseComp with context management. The model is optimized for efficient reasoning and task decomposition, completing the SWE-Bench Verified evaluation 37% faster than its predecessor M2.

Key quotes

· 4 pulled
Extensively trained with reinforcement learning in hundreds of thousands of complex real-world environments, M2.5 is SOTA in coding, agentic tool use and search, office work, and a range of other economically valuable tasks
boasting scores of 80.2% in SWE-Bench Verified, 51.3% in Multi-SWE-Bench, and 76.3% in BrowseComp (with context management)
Trained to reason efficiently and decompose tasks optimally, M2.5 exhibits tremendous speed in performing complicated agentic tasks
completing the SWE-Bench Verified evaluation 37% faster than M2
Snippet from the RSS feed
MiniMax M2.5: Built for Real-World Productivity.

You might also wanna read