MiniMax model product
MiniMax M2.7
7 is an LLM for software engineering, office tasks, and other complex productivity tasks.
Updated Sep 8, 2026. Default version: MiniMax M2.7
LLMBoard Score57.4MiniMax M2.7
Coverage20%8 benchmark families
Context window204.8KTokens
Official input price$0.30MiniMax (minimax.io) API
MiniMax M2.7 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
MiniMax M2.7 Benchmark Results
Benchmark scores for MiniMax M2.7.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMLE-Bench Lite | Score66.60% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMM-ClawBench | Score62.70% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMulti-SWE-Bench | Score52.70% | Rank01 | Participants6 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkVIBE-Pro | Score55.60% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkArtificial Analysis | Score50.00% | Rank07 | Participants8 | Percentile14.29% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score76.50% | Rank11 | Participants43 | Percentile76.19% | EvidenceC | Evaluated |
| BenchmarkNL2Repo | Score39.80% | Rank19 | Participants22 | Percentile14.29% | EvidenceC | Evaluated |
| BenchmarkFinance Agent v2 | Score27.89% | Rank26 | Participants26 | Percentile0.00% | EvidenceB | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score57.00% | Rank26 | Participants51 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkToolathlon | Score46.30% | Rank30 | Participants41 | Percentile27.50% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Tool Hallucination | Score0.61% | Rank30 | Participants49 | Percentile39.58% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Pro | Score56.20% | Rank33 | Participants55 | Percentile40.74% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Steerability | Score-5.33% | Rank40 | Participants49 | Percentile18.75% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Bash Recovery Steps | Score-19.57% | Rank44 | Participants49 | Percentile10.42% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Leaderboard | Score-11.71% | Rank46 | Participants49 | Percentile6.25% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Task Outcome Explicit | Score-15.18% | Rank46 | Participants49 | Percentile6.25% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Praise Complaint | Score-19.07% | Rank49 | Participants49 | Percentile0.00% | EvidenceA | Evaluated |
| BenchmarkLM Arena Webdev | Score1,398.47 rating | Rank60 | Participants97 | Percentile38.54% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,421.61 rating | Rank86 | Participants121 | Percentile29.17% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,415.36 rating | Rank93 | Participants210 | Percentile55.98% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,404.64 rating | Rank99 | Participants210 | Percentile53.11% | EvidenceA | Evaluated |
MiniMax M2.7 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenaagent tool hallucination | Categoryoverall | Rank30 | Rating / score0.01 | VotesN/A | Observations772.3K | Result date |
| Arenatext factuality | Categoryjapanese | Rank34 | Rating / score1,323.02 | Votes497 | ObservationsN/A | Result date |
| Arenatext factuality | Categorygerman | Rank39 | Rating / score1,374.83 | Votes581 | ObservationsN/A | Result date |
| Arenaagent steerability | Categoryoverall | Rank40 | Rating / score-0.05 | VotesN/A | Observations17.4K | Result date |
| Arenatext factuality | Categorykorean | Rank41 | Rating / score1,327.94 | Votes651 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank41 | Rating / score1,393.66 | Votes838 | ObservationsN/A | Result date |
| Arenaagent bash recovery steps | Categoryoverall | Rank44 | Rating / score-0.20 | VotesN/A | Observations30.2K | Result date |
| Arenaagent | Categoryoverall | Rank46 | Rating / score-0.12 | VotesN/A | Observations842.5K | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank46 | Rating / score-0.15 | VotesN/A | Observations17.2K | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank49 | Rating / score-0.19 | VotesN/A | Observations5.5K | Result date |
| Arenatext factuality | Categoryfrench | Rank56 | Rating / score1,443.97 | Votes1,928 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank56 | Rating / score1,415.79 | Votes1,596 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-react | Rank56 | Rating / score1,387.83 | Votes11,959 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank57 | Rating / score1,491.60 | Votes17,619 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank57 | Rating / score1,432.47 | Votes2,699 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank58 | Rating / score1,426.44 | Votes2,630 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-html | Rank59 | Rating / score1,403.63 | Votes1,828 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank60 | Rating / score1,459.45 | Votes5,094 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank60 | Rating / score1,398.47 | Votes15,089 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank60 | Rating / score1,398.47 | Votes15,089 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank62 | Rating / score1,471.77 | Votes17,906 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank64 | Rating / score1,453.55 | Votes18,875 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry legal and government | Rank66 | Rating / score1,434.78 | Votes3,957 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank68 | Rating / score1,439.36 | Votes6,246 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry medicine and healthcare | Rank68 | Rating / score1,450.06 | Votes3,523 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank70 | Rating / score1,472.92 | Votes25,921 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank71 | Rating / score1,423.15 | Votes20,492 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank72 | Rating / score1,441.24 | Votes19,030 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank72 | Rating / score1,451.35 | Votes2,878 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank72 | Rating / score1,431.74 | Votes11,322 | ObservationsN/A | Result date |
MiniMax M2.7 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 $0.08 input, $0.32 output per 1M via DevPass (LLM Gateway)
- Tracked offerings
- 60
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNvidia | Provider model IDminimaxai/minimax-m2.7 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderKenari | Provider model IDminimax-m2-7 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderKenari | Provider model IDminimax-m2-7-highspeed | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderMiniMax Token Plan (minimaxi.com) | Provider model IDMiniMax-M2.7 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderMiniMax Token Plan (minimaxi.com) | Provider model IDMiniMax-M2.7-highspeed | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderUnoRouter | Provider model IDminimax-m2.7:free | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderMiniMax Token Plan (minimax.io) | Provider model IDMiniMax-M2.7 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderMiniMax Token Plan (minimax.io) | Provider model IDMiniMax-M2.7-highspeed | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderSCNet Token Plan | Provider model IDMiniMax-M2.7 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDminimax-m2.7 | Regionglobal | Input / 1M$0.08 | Output / 1M$0.32 | Context204.8K | Updated |
| ProviderEmpirioLabs AI | Provider model IDminimax-m2-7 | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context200K | Updated |
| ProviderDeep Infra | Provider model IDMiniMaxAI/MiniMax-M2.7 | Regionglobal | Input / 1M$0.25 | Output / 1M$1 | Context196.6K | Updated |
| ProviderPioneer | Provider model IDMiniMaxAI/MiniMax-M2.7 | Regionglobal | Input / 1M$0.279 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderOrcaRouter | Provider model IDminimax/minimax-m2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderHugging Face | Provider model IDMiniMaxAI/MiniMax-M2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderOpenRouter | Provider model IDminimax/minimax-m2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderAuriko | Provider model IDminimax-m2-7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderAlibaba (China) | Provider model IDMiniMax/MiniMax-M2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderOpenCode Go | Provider model IDminimax-m2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderLLM Gateway | Provider model IDminimax/minimax-m2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderMerge Gateway | Provider model IDminimax/minimax-m2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderFastRouter | Provider model IDminimax/minimax-m2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderGMI Cloud | Provider model IDMiniMaxAI/MiniMax-M2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context196.6K | Updated |
| ProviderTogether AI | Provider model IDMiniMaxAI/MiniMax-M2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context202.8K | Updated |
| ProviderOfox | Provider model IDminimax/minimax-m2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| Provider302.AI | Provider model IDMiniMax-M2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderOpenCode Zen | Provider model IDminimax-m2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
| ProviderRequesty | Provider model IDminimax-m2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context200K | Updated |
| ProviderFrogBot | Provider model IDminimax-m2-7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context192K | Updated |
| ProviderMiniMax (minimaxi.com) | Provider model IDMiniMax-M2.7 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context204.8K | Updated |
MiniMax M2.7 Runtime Performance
Provider-specific output speed and catalog latency for MiniMax M2.7. 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 M2.7 Specifications
Technical details for the model's default version.
- Version
- MiniMax M2.7
- Released
- Mar 18, 2026
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 204.8K
- Max output
- 196.6K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- MIT
MiniMax M2.7 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 M2.7 | Released | LLMBoard57.36 | ParametersN/A | Context204.8K | Max output196.6K | Open weightsNo | LicenseMIT |
Models similar to MiniMax M2.7
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MI
MiniMax M2.5
MiniMax
MI
MiniMax M2.1
MiniMax
MI
MiniMax M3
MiniMax
MI
MiniMax M2
MiniMax
MI
MiniMax M1 80K
MiniMax
MI
MiniMax M1 40K
MiniMax
What is MiniMax M2.7?
Key information about MiniMax M2.7 and its available data.
7 is a MiniMax large language model that supports complex agent harnesses, software engineering tasks, log analysis, code security, machine learning tasks, and Office Suite editing. 22% on SWE-Pro, has a 1495 ELO on GDPval-AA, and maintains 97% skill adherence on 40 complex skills cases.
Data as of 2026-09-08.
FAQ
Common questions about MiniMax M2.7.
When was MiniMax M2.7 released?
MiniMax M2.7's default version was released on Mar 18, 2026.
How much does MiniMax M2.7 cost?
MiniMax M2.7'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 $0.08 input and $0.32 output via DevPass (LLM Gateway).
Who created MiniMax M2.7?
MiniMax M2.7 was created by MiniMax.
What is the context window for MiniMax M2.7?
The default version has a 204.8K token context window.
Is MiniMax M2.7 open weight?
No. The default version is not marked as having publicly available weights.