MiniMax-M3
MiniMax-M3 is an open-weights AI model from MiniMax with an index score of 147 (GPT-4 = 100), rank 74 of 217.
147131–164Index score#74 of 217 models
$0.30/ $1.2Price per million tokensinput / output · via OpenRouter
1.05MContext windowtokens it reads at once
1 Jun 2026Released6 months ago
Where it sitson the frontier
Grok 4 reached this score 11 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
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 11 leaderboards
The Model Indexthird-party tests, our method#74of 217 · 147
LMArena · Codingcoding questions in chat#80of 357 · 1493LMArena · Instruction followingfollowing detailed instructions#84of 362 · 1428LMArena · Textoverall chat quality, judged by people#87of 362 · 1436LMArena · Long promptslong, complex requests#85of 340 · 1445LMArena · Creative writingcreative writing#95of 360 · 1396LMArena · Mathsmaths questions in chat#101of 346 · 1425Epoch Capabilities Indexoverall capability from many benchmarks#78of 231 · 147.9LMArena · Visionunderstanding images#60of 145 · 1232LMArena · WebDevbuilding web apps and front ends#67of 133 · 1484LMArena · Documentsworking with long documents#29of 40 · 1437Best attop three among current models
Not in the top three among current models on any category we track.
Where to use itprices checked 18 Nov 2026
API providers 6 · per 1M tokens, in / out
Run it yourself
Official weightsMiniMaxAI/Minimax-M3↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released1 Jun 2026
Announcementhuggingface.co ↗
Release entryMiniMax-M3
Scored asMiniMax-M3
Output speed–
Hugging FaceMiniMaxAI/Minimax-M3 ↗