I Built the Same App With MiniMax M3 and Composer
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Related videos
My Honest Thoughts on AI and the Job Market in 2026 (No Hype)
Tech With Tim
24.9k views
The Only AI Coding Tools Worth Learning in 2026
Tech With Tim
38.1k views
Lovable vs MeDo, which AI app builder actually works?
Tech With Tim
87.9k views
Master Python Requests In 15 Minutes. Call Any API
Tech With Tim
31.3k views
Build & Deploy a Python AI Agent in 20 Minutes
Tech With Tim
38.6k views
Tim Miller: Trump Completely Lost Touch with America
The Bulwark
124.2k views
I Let 3 AIs Compete to Build the Same App…
Tech With Tim
4.3m views
Build a Python AI Agent in 10 Minutes
Tech With Tim
84.2k views
I Built an Entire App with OpenAI's Codex and 8 AI Agent Employees
Greg Isenberg
224.4k views
How to Build AI Agents in Python
Tech With Tim
46.7k views
Top Comments (10)
dude, GLM-5.2 is the new GOAT of AI models.
Get a MiniMax Token Plan with 12% OFF: https://platform.minimax.io/subscribe/coding-plan?code=7kk2uAhnPa&source=link
Hey Tim would you mine to compare minimax and Glm 2.5 pls
will this work with vscod in the future
Would love to see your review between GPT 5.5 and GLM 5.2
I'm looking for somebody to test these models with Rust, not python nor js nor typescript nor C/C++/C# and nor java. Edit: ah, you also test with rust. Great!
Hey please make a video how to train and fine tune your own video generater model
Why do you look exhausted?
yest i ran a similar comparison - more tools, but cursor with composer & open code with minimax were the clear outliers. task for comparison was brainstorming - same prompt in all cases, was curious of results. junie, gh copilot = meh results, antigravity with gemini = similarly meh, it clearly shined in visual design and jumped to it quickly, but the brainstorming part was still similarly meh. composer did a much better job, kept grilling me asking me questions for hours. minimax did the same thing, just even more thoroughly, more questions, more details, it actually got me tired. asked for edge cases too. much more solid result. i guess i know which ide and which coding agent i will be using :)
I'd love to see a MM3 evaluation which includes the native MM desktop harness. This is a good opportunity to explain how the two work hand in glove and compare it with other harnesses/models, ie. Claude Code vs MM Code, maybe MM3 v Haiku (models).
Unlock the Data Inside
Turn Videos into Knowledge
- Get FREE 10/day: transcripts, summaries, chats
- Chat with videos, export text & PDF
- $1 free API credit for RAG, chatbots & research
Free forever plan • All features unlocked
Top Comments (10)
dude, GLM-5.2 is the new GOAT of AI models.
Get a MiniMax Token Plan with 12% OFF: https://platform.minimax.io/subscribe/coding-plan?code=7kk2uAhnPa&source=link
Hey Tim would you mine to compare minimax and Glm 2.5 pls
will this work with vscod in the future
Would love to see your review between GPT 5.5 and GLM 5.2
I'm looking for somebody to test these models with Rust, not python nor js nor typescript nor C/C++/C# and nor java. Edit: ah, you also test with rust. Great!
Hey please make a video how to train and fine tune your own video generater model
Why do you look exhausted?
yest i ran a similar comparison - more tools, but cursor with composer & open code with minimax were the clear outliers. task for comparison was brainstorming - same prompt in all cases, was curious of results. junie, gh copilot = meh results, antigravity with gemini = similarly meh, it clearly shined in visual design and jumped to it quickly, but the brainstorming part was still similarly meh. composer did a much better job, kept grilling me asking me questions for hours. minimax did the same thing, just even more thoroughly, more questions, more details, it actually got me tired. asked for edge cases too. much more solid result. i guess i know which ide and which coding agent i will be using :)
I'd love to see a MM3 evaluation which includes the native MM desktop harness. This is a good opportunity to explain how the two work hand in glove and compare it with other harnesses/models, ie. Claude Code vs MM Code, maybe MM3 v Haiku (models).