Thoughts on AI, technology, and the future we're building.

New posts every week

HomeAll PostsAI NewsAI Basics
Timelines
ChatGPTOpenAI release historyAnthropic ClaudeClaude release historyGoogle GeminiGemini release history
Benchmarks
OverviewFull model trackerValue RankingsPerformance for the moneyCoding RankingsSWE-bench and code signalsAgent RankingsTool and workflow signalsReasoning RankingsKnowledge and reasoningLong ContextDocument and retrieval signalsLab ComparisonsProvider-level rankings
CategoriesAboutContact

Subscribe to Newsletter

Practical AI news, tips, tricks, tool analysis, sent straight to your inbox.

No spam. Unsubscribe anytime.

Practical explainers, tool notes, and systems thinking for people turning new AI capability into useful work.

Explore

  • All Posts
  • Categories
  • About
  • Contact

Categories

  • AI News
  • AI Basics
  • ChatGPT
  • Anthropic
  • AI Tools
  • AI Video
  • AI Images
  • Courses

Connect

LinkedInTwitterRSS

© 2026. All rights reserved.

Benchmark suiteUpdated May 27, 2026

MiniMax benchmarks.

A lab-level profile for MiniMax, covering tracked models, category leaders, open/proprietary mix, speed, value, source coverage, and portfolio depth.

All labs

Lab rank

#6

By available Arena average

Models tracked

4

4 open-weight models

Portfolio coverage

53%

Average matched benchmark signals

Fastest model

1.06s

Minimax M2

OverviewFull public trackerValuePerformance for the moneyCodingCode and SWE-bench signalsAgentsTool and workflow readinessReasoningKnowledge and reasoning signalsContextDocument and retrieval signalsLabsProvider comparisons

Lab profile

Portfolio shape, leaders, and model coverage.

The lab page now starts with the portfolio read, then drills into category leaders, value rankings, and model-level coverage rather than repeating source panels.

Portfolio read

MiniMax has 4 tracked benchmark profiles.

Lab #6

The portfolio combines 0 proprietary models and 4 open-weight models. Its average available Arena rank is 55, with a best category rank of #34. Average profile coverage is 53%, so model-level gaps remain visible in the cards below.

Best Arena model

Minimax M2.7

Best category rank #34

Highest coverage

Minimax M2.7

56% matched signals

Fastest response

Minimax M2

1.06s first token

Access mix

Open versus proprietary

Proprietary

0 / 0%

Open weights

4 / 100%

Value leader

Minimax M2.1 Preview

Category leaders

Best model by benchmark lens.

Each card shows the highest-ranked model from this lab in a composite benchmark suite, with the global rank and index left intact.

Value

Quality, price, latency, and speed

Minimax M2.1 Preview

#1573

value index

Coding

Code Arena, SWE-bench, and output speed

Minimax M2.5

#1973

coding index

Agents

Search, document, code, and latency

Minimax M2.7

#5979

agent proxy

Reasoning

Text, document, vision, and mode signals

Minimax M2.7

#1472

reasoning proxy

Context

Document, search, and text proxy

Minimax M2.7

#1172

context proxy

MiniMax value ranking table

Models from this lab with both quality and commercial price matches.

Top 4 of 4

RankModelIndexPriceLatencySpeedQualitySources
#15
Minimax M2.1 Preview

minimax-m2.1-preview

MiniMaxOpen weights
73value index
$0.525blended / 1M tokens
2.36stime to first token
203 tok/soutput speed
63quality signal
ArenaArtificial Analysis
#16
Minimax M2.5

minimax-m2.5

MiniMaxOpen weights
72value index
$0.525blended / 1M tokens
2.33stime to first token
205 tok/soutput speed
61quality signal
ArenaArtificial Analysis
#41
Minimax M2

minimax-m2

MiniMaxOpen weights
62value index
$0.525blended / 1M tokens
1.06stime to first token
101 tok/soutput speed
45quality signal
ArenaArtificial Analysis
#62
Minimax M2.7

minimax-m2.7

MiniMaxOpen weights
54value index
$0.525blended / 1M tokens
2.68stime to first token
66 tok/soutput speed
31quality signal
ArenaArtificial Analysis
#15
Minimax M2.1 Preview

minimax-m2.1-preview

MiniMaxOpen weights
73value index
Price
$0.525blended / 1M tokens
Latency
2.36stime to first token
Speed
203 tok/soutput speed
Quality
63quality signal
ArenaArtificial Analysis
#16
Minimax M2.5

minimax-m2.5

MiniMaxOpen weights
72value index
Price
$0.525blended / 1M tokens
Latency
2.33stime to first token
Speed
205 tok/soutput speed
Quality
61quality signal
ArenaArtificial Analysis
#41
Minimax M2

minimax-m2

MiniMaxOpen weights
62value index
Price
$0.525blended / 1M tokens
Latency
1.06stime to first token
Speed
101 tok/soutput speed
Quality
45quality signal
ArenaArtificial Analysis
#62
Minimax M2.7

minimax-m2.7

MiniMaxOpen weights
54value index
Price
$0.525blended / 1M tokens
Latency
2.68stime to first token
Speed
66 tok/soutput speed
Quality
31quality signal
ArenaArtificial Analysis

Model portfolio

MiniMax model coverage map.

Every tracked model keeps its best Arena rank, coverage score, commercial metrics, and suite placement visible in one scannable grid.

Minimax M2.7

minimax-m2.7

Open weights

Coverage

56%

Best Arena

#34

Code

Value

#62

value index

Coding

#47

coding index

Latency

2.68s

66 tok/s

$0.525

Minimax M2.1 Preview

minimax-m2.1-preview

Open weights

Coverage

44%

Best Arena

#38

Code

Value

#15

value index

Coding

#46

coding index

Latency

2.36s

203 tok/s

$0.525

Minimax M2.5

minimax-m2.5

Open weights

Coverage

56%

Best Arena

#45

Code

Value

#16

value index

Coding

#19

coding index

Latency

2.33s

205 tok/s

$0.525SWE #3

Minimax M2

minimax-m2

Open weights

Coverage

56%

Best Arena

#62

Code

Value

#41

value index

Coding

#53

coding index

Latency

1.06s

101 tok/s

$0.525SWE #25