llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsMiniMax M2.5

MiniMax model product

MiniMax M2.5

MiniMax M2.5 is the world's first production-level model designed natively for Agent scenarios. Building on the M2.1 foundation, M2.5 delivers significant improvements in programming, tool calling, search, and office productivity. With only 10B activation parameters from its 230B MoE architecture, it achieves competitive performance against top international models like Claude Opus 4.6 while maintaining high throughput and efficient inference. M2.5 supports full-stack development for PC, App, and cross-platform applications, and excels in agentic workflows including automated customer support, data-analysis pipelines, and complex task execution.

Updated Aug 10, 2026. Default version: MiniMax M2.5

Compare
LLMBoard scoreN/ANot scored
CoverageN/ANo published score
Context window204.8KTokens
Official input price$0.30MiniMax (minimax.io) API

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
MiniMax M2.5
Released
Feb 12, 2026
Knowledge cutoff
Unknown
Parameters
230B
Context window
204.8K
Max output
131.1K
Inputs
image, text
Outputs
text
Open weights
Yes
License
MIT

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

No capability profile

No published version under this unique model currently has enough benchmark coverage to calculate a score.

Benchmark results

Published benchmark records for the scored version currently unavailable.

No benchmark rows

No published benchmark result is linked to the scored version.

Arena results

Preference and agent-evaluation signals from published Arena datasets.

88 rows
Columns

Show columns

text factualitypolish551349.1597N/AAug 6, 2026
webdevwebdev-html601414.5898N/AAug 6, 2026
webdevwebdev-react641375.26,250N/AAug 6, 2026
text factualityspanish651375.8872N/AAug 6, 2026
text factualityfrench681393.1873N/AAug 6, 2026
webdevoverall681386.07,173N/AAug 6, 2026
webdevwebdev681386.07,173N/AAug 6, 2026
text factualityindustry mathematical841392.51,585N/AAug 6, 2026
text factualitymath851385.81,693N/AAug 6, 2026
text factualitychinese881419.11,516N/AAug 6, 2026
text factualityindustry medicine and healthcare981411.72,131N/AAug 6, 2026
text factualityindustry legal and government991409.22,209N/AAug 6, 2026
text factualityexpert1011403.42,494N/AAug 6, 2026
text factualityrussian1021378.63,113N/AAug 6, 2026
text factualitycreative writing1131359.44,527N/AAug 6, 2026
text factualityindustry entertainment and sports and media1151353.36,072N/AAug 6, 2026
text factualitymulti turn1161391.25,365N/AAug 6, 2026
text factualityindustry life and physical and social science1171400.54,834N/AAug 6, 2026
text factualityindustry writing and literature and language1191372.07,316N/AAug 6, 2026
text factualityhard prompts english1221424.710,280N/AAug 6, 2026
text factualityinstruction following1221383.210,881N/AAug 6, 2026
text factualitylonger query1221396.912,931N/AAug 6, 2026
text factualitycoding1231428.08,735N/AAug 6, 2026
text style controlgerman1231386.3621N/AAug 6, 2026
text factualityindustry business and management and financial operations1241385.55,925N/AAug 6, 2026
text factualityindustry software and it services1281421.814,562N/AAug 6, 2026
text factualityenglish1301407.518,603N/AAug 6, 2026
text style controlexpert1301420.23,441N/AAug 6, 2026
text factualityhard prompts1321409.525,086N/AAug 6, 2026
text style controlhard prompts english1321430.412,268N/AAug 6, 2026
text style controlenglish1341414.318,876N/AAug 6, 2026
text factualityexclude ties1351366.330,488N/AAug 6, 2026
text style controlindustry software and it services1351435.215,684N/AAug 6, 2026
text factualityoverall1361386.740,357N/AAug 6, 2026
text factualitynon english1371362.521,615N/AAug 6, 2026
text style controlcoding1371443.910,772N/AAug 6, 2026
text style controlchinese1381428.62,145N/AAug 6, 2026
text style controlrussian1381388.84,462N/AAug 6, 2026
text style controlindustry business and management and financial operations1391399.07,934N/AAug 6, 2026
text style controlindustry legal and government1391404.03,104N/AAug 6, 2026
textgerman1411358.4621N/AAug 6, 2026
text style controlfrench1421398.71,220N/AAug 6, 2026
text style controlindustry entertainment and sports and media1421360.97,895N/AAug 6, 2026
text style controlindustry mathematical1421400.52,217N/AAug 6, 2026
text style controllonger query1421402.714,974N/AAug 6, 2026
text style controlmath1441396.12,422N/AAug 6, 2026
text style controlhard prompts1451414.925,291N/AAug 6, 2026
textexpert1461373.33,441N/AAug 6, 2026
text style controlindustry life and physical and social science1461407.76,656N/AAug 6, 2026
text style controlmulti turn1461394.37,285N/AAug 6, 2026
text style controlcreative writing1471357.46,281N/AAug 6, 2026
text style controlindustry writing and literature and language1471370.29,513N/AAug 6, 2026
text style controlpolish1471366.0877N/AAug 6, 2026
text style controlexclude ties1481370.630,731N/AAug 6, 2026
text style controloverall1501389.940,688N/AAug 6, 2026
text style controlindustry medicine and healthcare1511408.93,014N/AAug 6, 2026
text style controlinstruction following1511380.212,840N/AAug 6, 2026
textindustry mathematical1521379.92,217N/AAug 6, 2026
texthard prompts english1531385.112,268N/AAug 6, 2026
text style controlspanish1531370.21,287N/AAug 6, 2026
textchinese1561390.42,145N/AAug 6, 2026
textfrench1561358.91,220N/AAug 6, 2026
textmath1561380.82,422N/AAug 6, 2026
textenglish1571382.818,876N/AAug 6, 2026
textinstruction following1571351.712,840N/AAug 6, 2026
textlonger query1581363.614,974N/AAug 6, 2026
textpolish1581328.5877N/AAug 6, 2026
textindustry business and management and financial operations1591355.47,934N/AAug 6, 2026
texthard prompts1601369.525,291N/AAug 6, 2026
textindustry writing and literature and language1601346.69,513N/AAug 6, 2026
textspanish1601348.51,287N/AAug 6, 2026
textrussian1611352.34,462N/AAug 6, 2026
text style controlnon english1611363.921,812N/AAug 6, 2026
textcreative writing1651331.16,281N/AAug 6, 2026
textindustry entertainment and sports and media1651328.67,895N/AAug 6, 2026
textindustry legal and government1651366.23,104N/AAug 6, 2026
textindustry software and it services1651381.215,684N/AAug 6, 2026
textmulti turn1651361.47,285N/AAug 6, 2026
textcoding1671378.110,772N/AAug 6, 2026
textindustry life and physical and social science1691367.66,656N/AAug 6, 2026
textoverall1701358.440,688N/AAug 6, 2026
textexclude ties1701325.330,731N/AAug 6, 2026
textindustry medicine and healthcare1721359.23,014N/AAug 6, 2026
textnon english1741333.021,812N/AAug 6, 2026
textkorean1851223.8688N/AAug 6, 2026
text style controlkorean1881262.6688N/AAug 6, 2026
textjapanese2061142.5339N/AAug 6, 2026
text style controljapanese2171171.1339N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
$0.30 input, $1.2 output per 1M
Official provider
MiniMax (minimax.io)
Lowest third-party
From $0.11 input, $0.95 output per 1M via CrofAI
Tracked offerings
20
19 rows
Columns

Show columns

Alibaba Coding Plan (China)MiniMax-M2.5globalN/AN/A196.6KAug 7, 2026
Alibaba Coding PlanMiniMax-M2.5globalN/AN/A196.6KAug 7, 2026
Alibaba Token PlanMiniMax-M2.5globalN/AN/A196.6KAug 7, 2026
Tencent Coding Plan (China)minimax-m2.5globalN/AN/A204.8KAug 7, 2026
MiniMax Token Plan (minimax.io)MiniMax-M2.5globalN/AN/A204.8KAug 7, 2026
Alibaba Token Plan (China)MiniMax-M2.5globalN/AN/A196.6KAug 7, 2026
MiniMax Token Plan (minimaxi.com)MiniMax-M2.5globalN/AN/A204.8KAug 7, 2026
CrofAIminimax-m2.5global$0.11$0.95204.8KAug 7, 2026
GreenPTminimax-m2.5global$0.1938$1.13204.8KAug 7, 2026
DInferenceminimax-m2.5global$0.22$0.88200KAug 7, 2026
DigitalOceanminimax-m2.5global$0.225$0.9065.5KAug 7, 2026
Cortecsminimax-m2.5global$0.296$1.09196.7KAug 7, 2026
OpenCode Gominimax-m2.5global$0.30$1.2204.8KAug 7, 2026
LLM Gatewayminimax-m2.5global$0.30$1.2228.7KAug 7, 2026
OpenCode Zenminimax-m2.5global$0.30$1.2204.8KAug 7, 2026
MiniMax (minimax.io)MiniMax-M2.5global$0.30$1.2204.8KAug 7, 2026
Alibaba (China)MiniMax-M2.5global$0.30$1.2204.8KAug 7, 2026
MiniMax (minimaxi.com)MiniMax-M2.5global$0.30$1.2204.8KAug 7, 2026
Regolo AIminimax-m2.5global$0.80$3.5190KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

MiniMax M2.5 versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

MiniMax M2.5Feb 12, 2026N/A230B204.8K131.1KYesMIT

What is MiniMax M2.5?

A concise description based on the published model registry.

MiniMax M2.5 is the world's first production-level model designed natively for Agent scenarios. Building on the M2.1 foundation, M2.5 delivers significant improvements in programming, tool calling, search, and office productivity. With only 10B activation parameters from its 230B MoE architecture, it achieves competitive performance against top international models like Claude Opus 4.6 while maintaining high throughput and efficient inference. M2.5 supports full-stack development for PC, App, and cross-platform applications, and excels in agentic workflows including automated customer support, data-analysis pipelines, and complex task execution.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Models similar to MiniMax M2.5

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#99
MI

MiniMax M2

MiniMax

44.9 LLMBoard

DetailsCompare
#89
MI

MiniMax M1 40K

MiniMax

48.5 LLMBoard

DetailsCompare
#68
MI

MiniMax M2.1

MiniMax

54.8 LLMBoard

DetailsCompare
#62
MI

MiniMax M1 80K

MiniMax

56.3 LLMBoard

DetailsCompare
#170
AC

Qwen3.5 0.8B

Alibaba Cloud / Qwen Team

0.3 LLMBoard

DetailsCompare
#169
GO

Gemma 3 1B

Google

2.7 LLMBoard

DetailsCompare

FAQ

Common questions about MiniMax M2.5.

When was MiniMax M2.5 released?

MiniMax M2.5's default version was released on Feb 12, 2026.

How much does MiniMax M2.5 cost?

MiniMax M2.5'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 $0.11 input and $0.95 output via CrofAI.

Who created MiniMax M2.5?

MiniMax M2.5 is published under MiniMax in the model registry.

What is the context window for MiniMax M2.5?

The default version has a 204.8K token context window.

Is MiniMax M2.5 open weight?

Yes. The default version is marked as open weight under MIT.

How many API providers offer MiniMax M2.5?

20 published provider offerings are linked to the default version.

What models should I compare MiniMax M2.5 with?

No nearby ranked alternatives are currently available.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai