MiniMax-M2.1
MiniMax-M2.1 is an open-weights AI model from MiniMax with an index score of 135 (GPT-4 = 100), rank 113 of 217.
135117–153Index score#113 of 217 models
–Price per million tokensno public API price found
–Context windowtokens it reads at once
23 Dec 2025ReleasedReplaced by MiniMax-M2.5
Where it sitson the frontier
o1 reached this score 13 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsno evidence yet
Professional workevidence
Novel problemsno evidence yet
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 8 leaderboards
The Model Indexthird-party tests, our method#113of 217 · 135
LMArena · Instruction followingfollowing detailed instructions#137of 362 · 1385LMArena · Long promptslong, complex requests#132of 340 · 1407LMArena · Codingcoding questions in chat#141of 357 · 1437LMArena · Creative writingcreative writing#146of 360 · 1345LMArena · Mathsmaths questions in chat#144of 346 · 1389LMArena · Textoverall chat quality, judged by people#151of 362 · 1384LMArena · WebDevbuilding web apps and front ends#96of 133 · 1384Best attop three among current models
Replaced by MiniMax-M2.5; it no longer leads any category among current models.
Where to use itprices checked 18 Nov 2026
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released23 Dec 2025
Announcementhuggingface.co ↗
Release entryMiniMax-M2.1
Scored asMiniMax-M2.1
Output speed–
Hugging Facenot linked