NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/MiniMax M2.7
minimax logo

MiniMax M2.7

by minimax · Released Mar 2026

Open Source
51.2
avg score
Rank #137
Compare
Better than 56% of all models
Context
205K tokens (~102 books)
Input $/1M
$0.21
Output $/1M
$0.84
Type
text
License
Open Source
Benchmarks
17 tested
Data as of
About

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...

Tested on 17 benchmarks · BenchGecko score 51.2. Top scores: Chatbot Arena Elo — Overall (1415.0%), Chatbot Arena Elo — Coding (1397.0%), LiveBench — Mathematics (80.5%).

Looking for similar performance at lower cost?
Gemma 2 9B scores 51.1 (100% as good) at $0.03/1M input · 86% cheaper
Capabilities
coding
46.7
#108 globally
reasoning
65.6
#48 globally
math
80.5
#23 globally
knowledge
63.5
#37 globally
speed
38.8
#69 globally
general
8.2
#197 globally
language
64.0
#98 globally
Benchmark Scores
Compare All
Tested on 17 benchmarks · Ranked across 8 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
LiveBench — Coding

Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.

54.9·
LiveBench — Agentic Coding

LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.

50.0·
Terminal Bench

Complex terminal-based engineering tasks. Models must use command-line tools, navigate filesystems, and debug systems through shell interaction.

45.1·
reasoningCompare reasoning →
LiveBench — Reasoning

Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.

74.8·
LiveBench — Data Analysis

Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.

56.3·
mathCompare math →
LiveBench — Mathematics

Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.

80.5·
Quick compare:DeepSeek logovs DeepSeek V3.2Google DeepMind logovs Gemma 2 9BMicrosoft logovs Phi 3.5 Mini Instruct
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · minimax MiniMax M2.7
Mar 2026
51.2
$0.21/M in205Kctx17 benchmarks
Mar 2026
$0.00/M in(-0.21)197Kctx(-8K)
See the full MiniMax M2.7 family →
Recently Happened
MiniMax M2.7 pricing dropped 30%
Sep 29, 2026
MiniMax M2.7 pricing increased 25%
Aug 25, 2026
MiniMax M2.7 pricing increased 33%
Jul 10, 2026
MiniMax M2.7 pricing dropped 25%
Jun 26, 2026
Similar Models
DeepSeek logo
DeepSeek V3.2
DeepSeek
51.3$0.28/1M
Google DeepMind logo
Gemma 2 9B
Google DeepMind
51.1$0.03/1M
Microsoft logo
Phi 3.5 Mini Instruct
Microsoft
51.1n/a
Links
Info
minimaxPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@minimax
Source Code
GitHubHugging Face
BenchGecko API
minimax-m2-7
Specifications
  • Typetext
  • Context205K tokens (~102 books)
  • ReleasedMar 2026
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.001
Available On
minimax logominimax$0.21
Categories
codingreasoningmathknowledgespeedgenerallanguage
Learn More
context-windowtransformeropen weightstokens
Share & Export
Tweet
Related Models
DeepSeek logoDeepSeek V3.2
51.3
Google DeepMind logoGemma 2 9B
51.1
Microsoft logoPhi 3.5 Mini Instruct
51.1
minimax logoMiniMax M2.5
51.4
MiniMax M2.7 is an open-source text AI model by minimax, released in March 2026. It has an average benchmark score of 51.2. Context window: 205K tokens.

Related Models

DeepSeek V3.2 · DeepSeekGemma 2 9B · Google DeepMindPhi 3.5 Mini Instruct · MicrosoftMiniMax M2.5 · minimaxo4 Mini · OpenAI

Benchmarks

Chatbot Arena Elo — OverallChatbot Arena Elo — CodingLiveBench — MathematicsLiveBench — ReasoningLiveBench — Language

Related Pages

minimax · Providerminimax · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-10-05

  • MiniMax M2.7 by minimax. BenchGecko score 51.2, rank 137 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.21 input · $0.84 output per 1M tokens (as of 2026-10-05).
  • Sold by 7 providers (as of 2026-10-05): GMICloud (fp8) $0.21 in / $0.84 out · Novita (fp8) $0.27 in / $1.08 out · AtlasCloud (fp8) $0.30 in / $1.20 out · Minimax (fp8) $0.30 in / $1.20 out · Groq $0.60 in / $1.80 out · and 2 more. Every provider
  • Gecko Tests: Who Are You B (Knows who made it) · Tokenizer Tax A (35% more tokens outside English).

How to cite · data as of 2026-10-05

MiniMax M2.7 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/minimax-m2-7

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP