MiniMax model product
MiniMax M1 40K
MiniMax M1 40K is an open-source reasoning model with hybrid attention for long-context processing.
Updated Sep 8, 2026. Default version: MiniMax M1 40K
LLMBoard Score34.2MiniMax M1 40K
Coverage40%16 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
MiniMax M1 40K Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
MiniMax M1 40K Benchmark Results
Benchmark scores for MiniMax M1 40K.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkOpenAI-MRCR: 2 needle 1M | Score58.60% | Rank01 | Participants5 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOpenAI-MRCR: 2 needle 128k | Score76.10% | Rank02 | Participants9 | Percentile87.50% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score60.00% | Rank06 | Participants23 | Percentile77.27% | EvidenceC | Evaluated |
| BenchmarkLongBench v2 | Score61.00% | Rank08 | Participants17 | Percentile56.25% | EvidenceC | Evaluated |
| BenchmarkZebraLogic | Score80.10% | Rank08 | Participants8 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMATH-500 | Score96.00% | Rank16 | Participants32 | Percentile51.61% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Retail | Score67.80% | Rank16 | Participants25 | Percentile37.50% | EvidenceC | Evaluated |
| BenchmarkMulti-Challenge | Score44.70% | Rank18 | Participants29 | Percentile39.29% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score83.30% | Rank22 | Participants53 | Percentile59.62% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score62.30% | Rank34 | Participants75 | Percentile55.41% | EvidenceC | Evaluated |
| BenchmarkSimpleQA | Score17.90% | Rank37 | Participants47 | Percentile21.74% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score80.60% | Rank56 | Participants138 | Percentile59.85% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score74.60% | Rank84 | Participants119 | Percentile29.66% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score55.60% | Rank90 | Participants113 | Percentile20.54% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score7.20% | Rank96 | Participants103 | Percentile6.86% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score69.20% | Rank143 | Participants247 | Percentile42.28% | EvidenceC | Evaluated |
MiniMax M1 40K Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
MiniMax M1 40K Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
MiniMax M1 40K Runtime Performance
Provider-specific output speed and catalog latency for MiniMax M1 40K. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
MiniMax M1 40K Specifications
Technical details for the model's default version.
- Version
- MiniMax M1 40K
- Released
- Jun 16, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 456B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
MiniMax M1 40K Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionMiniMax M1 40K | Released | LLMBoard34.20 | Parameters456B | ContextN/A | Max outputN/A | Open weightsYes | LicenseMIT |
Models similar to MiniMax M1 40K
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MI
MiniMax M1 80K
MiniMax
MI
MiniMax M2
MiniMax
MI
MiniMax M2.1
MiniMax
MI
MiniMax M2.5
MiniMax
MI
MiniMax M2.7
MiniMax
MI
MiniMax M3
MiniMax
What is MiniMax M1 40K?
Key information about MiniMax M1 40K and its available data.
MiniMax M1 40K is an open-source, large-scale reasoning model developed by MiniMax. It supports a context window of up to 1 million tokens and reasoning outputs of up to 80,000 tokens.
Data as of 2026-09-08.
FAQ
Common questions about MiniMax M1 40K.
When was MiniMax M1 40K released?
MiniMax M1 40K's default version was released on Jun 16, 2025.
How much does MiniMax M1 40K cost?
No official standard PAYG price is currently available for MiniMax M1 40K.
Who created MiniMax M1 40K?
MiniMax M1 40K was created by MiniMax.
What is the context window for MiniMax M1 40K?
A context window is not available for the default version.
Is MiniMax M1 40K open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer MiniMax M1 40K?
No provider offering is currently linked to the default version.