Project AURIONAI Use-Cases Research & Innovation
MiniMax
multimodal LLM

MiniMax-M3

MiniMax's natively multimodal MoE model, successor to M2.x.

MiniMaxMiniMaxChinaMiniMax-MFamily
Charts comparing the efficiency of MiniMax-M3 attention with grouped query attention.
Levelmodel
Classmultimodal LLM
Parameters428B
Context1,000,000
Released1 Jun 2026
Opennessopen weights restricted
Runs onmulti-GPU node
Statusactive

Benchmark Results

vendor-reportedindependent
Arena Text leaderboardhuman preference arena
independent
no score in the notes
rank 96, Arena Text overall8 Oct 2026 arena.ai
Artificial Analysis Intelligence Index v4.3.2composite index
independent
29
03060

Score in index. Higher is better.

AA leaderboard, 205 current models10 Oct 2026 artificialanalysis.ai
BrowseCompagents and tool use
vendor-reported
83.5
050100

Score in %. Higher is better.

minimax.io
MMMU-Promultimodal
vendor-reported
78.1
050100

Score in %. Higher is better.

huggingface.co
SWE-bench Procoding
scaffold not statedvendor-reported
59
050100

Score in %. Higher is better.

huggingface.co
SWE-bench Verifiedcoding
vendor-reported
80.5
050100

Score in %. Higher is better.

huggingface.co
vendor-reported
80.5
050100

Score in %. Higher is better.

huggingface.co
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).

Lineage

successor
MiniMax-M2.5 to MiniMax-M2.7: successor, medium confidenceMiniMax-M2.7 to MiniMax-M3: successor, medium confidenceMiniMax-M2.5MiniMax-M2.5MiniMax, Feb 2026MiniMax-M2.7MiniMax-M2.7MiniMaxMiniMax-M3MiniMax-M3MiniMax, Jun 2026
MiniMaxMiniMax-M2.7 is the parent (successor)medium confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.

R&D Topics

Efficiency architectures (MoE, sparse attention, long context)produced byOpen-weight frontier releases as research substrateused by

Identity

Developer
MiniMax
Family
MiniMax-M
Released
1 Jun 2026 sourcessecondary report
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
MoE MoE with MiniMax Sparse Attention
Total parameters
428B sources
Active parameters
23B
Checkpoint parameters
–
Note
About 428B / 23B
Context length
1,000,000 tokens
Input
text, image, video
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights restricted
Licence
MiniMax Community License (M3) sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
multi-GPU node
Footprint
1M context (512K guaranteed). Estimate, unverified. Announced as open-weight, weights not yet public; the coding notes record minimax-community licence on HF.
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Industry Use Cases

No industry use case links this model.

Sources

  1. MiniMax M3 - Coding & Agentic Frontier, 1M Context, Multimodal minimax.io https://www.minimax.io/models/text/m3
  2. huggingface.co/MiniMaxAI/MiniMax-M3 https://huggingface.co/MiniMaxAI/MiniMax-M3
  3. LLM Leaderboard - Comparison of AI models from OpenAI, Anthropic, Google, SpaceXAI & others | Artificial Analysis artificialanalysis.ai https://artificialanalysis.ai/leaderboards/models
  4. Text Arena: LLM Rankings & AI Model Benchmarks arena.ai https://arena.ai/leaderboard/chat/text
  5. huggingface.co/MiniMaxAI/MiniMax-M3/blob/main/LICENSE https://huggingface.co/MiniMaxAI/MiniMax-M3/blob/main/LICENSE
  6. news.aibase.com/tw/news/28491 https://news.aibase.com/tw/news/28491
  7. huggingface.co/api/models/MiniMaxAI/MiniMax-M3 https://huggingface.co/api/models/MiniMaxAI/MiniMax-M3

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MiniMax-M3", https://aurion.semai.id/models/minimax-minimax-m3/, records of October 2026.