Effort not specified
MiniMaxAIReleased Jun 1, 2026
MiniMax-M3
MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.
Context window1M
Provider endpoints7
Benchmark results11
Measured performance
All leaderboards ↗Benchmark results
Effort not specified
GDPval-AA ↗2.1
1,242.47Effort not specified
AutomationBench-AA ↗AA Index 4.3.2 collection
21.25%Effort not specified
Effort not specified · Harness unreported
SciCode ↗AA Index 4.3.2 collection
47.11%AA · Under reviewEffort not specified
Humanity’s Last Exam ↗AA Index 4.3.2 collection
38.97%Effort not specified
GDP.pdf ↗AA Index 4.3.2 collection
9.8%Effort not specified
CritPt ↗AA Index 4.3.2 collection
3.71%AA · Under reviewEffort not specified
AA-Omniscience ↗AA Index 4.3.2 collection
1.35Effort not specified
AA-LCR ↗1.1
83%Effort not specified
Provider measurements
1 configurationSpeed
≈10K input tokens1 requestmedian / 72h
Artificial Analysis · first-party providers · serving endpoint not reported
MiniMax
MiniMax-M3
Reasoning Not reported
- Output rate
- 93.3839 tok/s
- Time to first chunk
- 1.18177 s
Last checked Source ↗
Methodology 2.2.0 & measurement details
First chunk includes request processing and network time, and may include reasoning.
- Prompt
- long · ≈10,000 input tokens
- Parallel requests
- 1
- Minimum answer
- 1,500 tokens
- Aggregation
- median over 72 hours
- Token counting
- o200k_base
- Benchmark client
- Google Cloud us-central1-a
- Serving endpoint
- Not reported
- Serving region
- Not reported
- Sample size
- Not reported
- Window end
- Not reported
Access & cost
8 quotesPrices across providers
Your token mix
USD · listed token ratesnovita
via Hugging Face- Input
- $0.30
- Output
- $1.20
together
via Hugging Face- Input
- $0.30
- Output
- $1.20
fireworks-ai
via Hugging Face- Input
- $0.30
- Output
- $1.20
featherless-ai
via Hugging Face- Input
- —
- Output
- —
deepinfra
via Hugging Face- Input
- $0.28
- Output
- $1.10
- Input
- $0.28
- Output
- $1.10
Fireworks AI
Standard · service_tier=default
- Input
- $0.30
- Output
- $1.20
- Cached input
- $0.06
Fireworks AI
Standard · service_tier=priority
- Input
- $0.45
- Output
- $1.80
- Cached input
- $0.09
Model specifications
- Developer
- MiniMaxAI
- Modality
- Language
- Context
- 1,000,000 tokens
- Maximum output
- Not reported
- Weights
- Open weights
- Released
- Jun 1, 2026
- Provider listed
- Jun 2, 2026
- First discovered
- Oct 16, 2026
Exact identities
- huggingface
MiniMaxAI/MiniMax-M3 - deepinfra
MiniMaxAI/MiniMax-M3 - artificial-analysis
277f939a-985b-4b37-859d-b3eabc7c0b26
Sources
Updated Oct 18, 2026
More from MiniMaxAI
View all ↗No reported score