MiniMax model product
MiniMax M2
MiniMax M2 is an open-source large language model by MiniMax for agentic workflows and coding tasks.
Updated Oct 23, 2026. Default version: MiniMax M2
LLMBoard Score42.4MiniMax M2
Coverage80%15 benchmark families
Context window1MTokens
Official input price$0.30MiniMax (minimax.io) API
MiniMax M2 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
MiniMax M2 Benchmark Results
Benchmark scores for MiniMax M2.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkIF | Score72.00% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkAA-Index | Score61.00% | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score46.30% | Rank04 | Participants25 | Percentile87.50% | EvidenceC | Evaluated |
| BenchmarkTau-bench | Score77.20% | Rank05 | Participants6 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkMulti-SWE-Bench | Score36.20% | Rank06 | Participants7 | Percentile16.67% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score83.00% | Rank08 | Participants76 | Percentile90.67% | EvidenceC | Evaluated |
| BenchmarkBrowseComp-zh | Score48.50% | Rank13 | Participants15 | Percentile14.29% | EvidenceC | Evaluated |
| BenchmarkTau2 Telecom | Score87.00% | Rank18 | Participants37 | Percentile52.78% | EvidenceC | Evaluated |
| BenchmarkSciCode | Score36.00% | Rank27 | Participants31 | Percentile13.33% | EvidenceC | Evaluated |
| BenchmarkAA AIME 2025 | Score78.33% | Rank35 | Participants96 | Percentile64.21% | EvidenceB | EvaluatedN/A |
| BenchmarkAA IFBench | Score72.31% | Rank37 | Participants168 | Percentile78.44% | EvidenceB | EvaluatedN/A |
| BenchmarkSWE-bench Multilingual | Score56.50% | Rank40 | Participants50 | Percentile20.41% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score82.00% | Rank46 | Participants142 | Percentile68.09% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score44.00% | Rank61 | Participants70 | Percentile13.04% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score69.40% | Rank74 | Participants120 | Percentile38.66% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score78.00% | Rank81 | Participants122 | Percentile33.88% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score12.50% | Rank91 | Participants109 | Percentile16.67% | EvidenceC | Evaluated |
| BenchmarkLM Arena Webdev | Score1,297.06 rating | Rank93 | Participants107 | Percentile13.21% | EvidenceA | Evaluated |
| BenchmarkAA CritPt | Score0.86% | Rank100 | Participants200 | Percentile50.25% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score23.23% | Rank102 | Participants201 | Percentile49.50% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score64.33% | Rank107 | Participants193 | Percentile44.79% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score13.67% | Rank109 | Participants200 | Percentile45.73% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score77.68% | Rank110 | Participants199 | Percentile44.95% | EvidenceB | EvaluatedN/A |
| BenchmarkGPQA | Score78.00% | Rank112 | Participants256 | Percentile56.47% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,359.85 rating | Rank129 | Participants131 | Percentile1.54% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,340.10 rating | Rank151 | Participants218 | Percentile30.88% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,343.51 rating | Rank158 | Participants218 | Percentile27.65% | EvidenceA | Evaluated |
MiniMax M2 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenawebdev | Categorywebdev-html | Rank92 | Rating / score1,306.35 | Votes6,685 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank93 | Rating / score1,297.06 | Votes6,714 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank93 | Rating / score1,297.06 | Votes6,714 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank117 | Rating / score1,371.69 | Votes742 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank118 | Rating / score1,318.30 | Votes615 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank120 | Rating / score1,405.76 | Votes911 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank122 | Rating / score1,357.42 | Votes133 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry writing and literature and language | Rank122 | Rating / score1,313.31 | Votes858 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank123 | Rating / score1,411.98 | Votes873 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank123 | Rating / score1,342.01 | Votes1,156 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank123 | Rating / score1,355.59 | Votes950 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts | Rank124 | Rating / score1,386.68 | Votes3,397 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank124 | Rating / score1,401.06 | Votes1,436 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank127 | Rating / score1,386.75 | Votes2,317 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexclude ties | Rank127 | Rating / score1,330.24 | Votes4,815 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank127 | Rating / score1,357.95 | Votes133 | ObservationsN/A | Result date |
| Arenatext factuality | Categorynon english | Rank129 | Rating / score1,330.09 | Votes3,477 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank129 | Rating / score1,359.85 | Votes6,693 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank135 | Rating / score1,361.43 | Votes1,096 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank136 | Rating / score1,311.75 | Votes280 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank137 | Rating / score1,376.09 | Votes1,649 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank139 | Rating / score1,366.67 | Votes315 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank143 | Rating / score1,335.80 | Votes135 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank144 | Rating / score1,356.90 | Votes3,748 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank144 | Rating / score1,368.13 | Votes301 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank144 | Rating / score1,372.75 | Votes2,458 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank144 | Rating / score1,358.20 | Votes1,096 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank145 | Rating / score1,370.60 | Votes1,550 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank145 | Rating / score1,326.18 | Votes206 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank146 | Rating / score1,366.04 | Votes452 | ObservationsN/A | Result date |
MiniMax M2 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.30 input, $1.2 output per 1M
- Official provider
- MiniMax (minimax.io)
- Lowest third-party
- From $0.17 input, $1.53 output per 1M via NanoGPT
- Tracked offerings
- 19
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderMiniMax Token Plan (minimax.cn) | Provider model IDMiniMax-M2 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderMiniMax Token Plan (minimax.io) | Provider model IDMiniMax-M2 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderNanoGPT | Provider model IDminimax/minimax-m2 | Regionglobal | Input / 1M$0.17 | Output / 1M$1.53 | Context200K | Updated |
| ProviderLLM Gateway | Provider model IDminimax/minimax-m2 | Regionglobal | Input / 1M$0.20 | Output / 1M$1 | Context196.6K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDminimax-m2 | Regionglobal | Input / 1M$0.20 | Output / 1M$1 | Context196.6K | Updated |
| ProviderOpenRouter | Provider model IDminimax/minimax-m2 | Regionglobal | Input / 1M$0.255 | Output / 1M$1.02 | Context204.8K | Updated |
| ProviderHugging Face | Provider model IDMiniMaxAI/MiniMax-M2 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderAmazon Bedrock | Provider model IDminimax.minimax-m2 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.6K | Updated |
| ProviderMerge Gateway | Provider model IDminimax/minimax-m2 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderZenMux | Provider model IDminimax/minimax-m2 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204K | Updated |
| ProviderOfox | Provider model IDminimax/minimax-m2 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderVercel AI Gateway | Provider model IDminimax/minimax-m2 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context205K | Updated |
| ProviderEden AI | Provider model IDminimax/MiniMax-M2 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderKilo Gateway | Provider model IDminimax/minimax-m2 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderMiniMax (minimax.io) | Provider model IDMiniMax-M2 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderQiniu | Provider model IDminimax/minimax-m2 | Regionglobal | Input / 1M$0.3043 | Output / 1M$1.22 | Context200K | Updated |
| ProviderMiniMax (minimax.cn) | Provider model IDMiniMax-M2 | Regionglobal | Input / 1M$0.3137 | Output / 1M$1.25 | Context204.8K | Updated |
| Provider302.AI | Provider model IDMiniMax-M2 | Regionglobal | Input / 1M$0.33 | Output / 1M$1.32 | Context1M | Updated |
| ProviderCortecs | Provider model IDminimax-m2 | Regionglobal | Input / 1M$0.349 | Output / 1M$1.41 | Context400K | Updated |
MiniMax M2 Runtime Performance
Provider-specific output speed and catalog latency for MiniMax M2. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderMiniMax | Output Speed70.00 tok/s | Catalog Latency4.00 s | Max Input1M | Max Output1M | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
MiniMax M2 Specifications
Technical details for the model's default version.
- Version
- MiniMax M2
- Released
- Oct 27, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 230B
- Context window
- 1M
- Max output
- 1M
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
MiniMax M2 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 M2 | Released | LLMBoard42.38 | Parameters230B | Context1M | Max output1M | Open weightsYes | LicenseMIT |
Models similar to MiniMax M2
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MI
MiniMax M1 80K
MiniMax
MI
MiniMax M2.1
MiniMax
MI
MiniMax M1 40K
MiniMax
MI
MiniMax M2.5
MiniMax
MI
MiniMax M2.7
MiniMax
MI
MiniMax M3
MiniMax
What is MiniMax M2?
Key information about MiniMax M2 and its available data.
MiniMax M2 is an open-source large language model designed for agents, coding, reasoning, and tool calling across Shell, Browser, Python, and other MCP tools. Its weights, API, and deployment guides are available on Hugging Face, vLLM, and SGLang.
Data as of 2026-10-22.
FAQ
Common questions about MiniMax M2.
When was MiniMax M2 released?
MiniMax M2's default version was released on Oct 27, 2025.
How much does MiniMax M2 cost?
MiniMax M2's official API price is $0.30 per million input tokens and $1.2 per million output tokens via MiniMax (minimax.io). The lowest tracked third-party offer starts at $0.17 input and $1.53 output via NanoGPT.
Who created MiniMax M2?
MiniMax M2 was created by MiniMax.
What is the context window for MiniMax M2?
The default version has a 1M token context window.
Is MiniMax M2 open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer MiniMax M2?
19 provider offerings are linked to the default version.