DataLearner logo
MI

MiniMax-M2.7

Reasoning modelMiniMax MMiniMax M2.7

MiniMax-M2.7

Release date: 2026-03-18Updated: 2026-07-17Views: 10,821
Live demoGitHubHugging FaceCompare
Parameters
229B
Context length
200K
Multilingual
Supported
Reasoning ability
4/5

MiniMax-M2.7 is a reasoning model from MiniMaxAI, released on 2026-03-18. It accepts text input and returns text output. The cataloged parameter count is 229B, with 10B active parameters per inference. The recorded context window is 200K, and the recorded maximum output is 200K. Cataloged capabilities include Reasoning model and Multilingual. The checkpoint is listed under the Minimax Modified Mit license, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

MiniMax-M2.7

Model basics

Reasoning traces
Supported
Thinking modes
Thinking Mode (Default)Standard Mode
Context length
200K tokens
Max output length
200K tokens
Model type
Reasoning model
Modality (in / out)
Text → Text
Release date
2026-03-18
Model file size
No data
MoE architecture
Yes
Total params / Active params
229B / 10B
Knowledge cutoff
No data
MiniMax-M2.7

Open source & experience

MiniMax-M2.7

Official resources

Paper
Paper
DataLearnerAI blog
DataLearnerAI blog
MiniMax-M2.7

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Learn about pricing modes
Standard
TypeConditionInputOutput
Text-$0.300/ 1M tokens$1.20/ 1M tokens
Cache PricingPrompt Cache
TypeTTLWriteRead
Text5m$0.375/ 1M tokens$0.060/ 1M tokens

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

MiniMax-M2.7

Benchmark Results

MiniMax-M2.7 currently shows benchmark results led by IF Bench (26 / 282, score 76), Claw Bench (5 / 29, score 91.70), Terminal Bench Hard (55 / 244, score 39). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage
Internet

General Knowledge

4 evaluations
Benchmark / mode
Score
Rank/total
LiveBench
Deep
63.49
57 / 117
HLE
Thinking Mode
29.60
210 / 565
HLE
Thinking Mode
28
226 / 565
CritPt
Thinking Mode
0.60
169 / 201

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Thinking Mode
87
134 / 463

Coding and Software Engineer

4 evaluations
Benchmark / mode
Score
Rank/total
SWE-bench Multilingual
Thinking ModeTools
76.50
10 / 30
SWE-Bench Pro - Public
Thinking ModeTools
56.20
29 / 62
SciCode
Thinking Mode
50.10
69 / 131
NL2Repo-Bench
Thinking ModeTools
39.80
16 / 16

Agent Level Benchmark

3 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench - Telecom
Thinking ModeTools
85
89 / 264
Terminal Bench Hard
Thinking ModeTools
39
55 / 244
τ³-Banking
Thinking ModeTools
9.90
132 / 167

Instruction Following

2 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Thinking Mode
75.70
31 / 282
IF Bench
Thinking ModeTools
76
26 / 282

AI Agent - Tool Usage

2 evaluations
Benchmark / mode
Score
Rank/total
Terminal Bench 2.0
Thinking ModeTools
57
25 / 48
Terminal-Bench 2.1
Thinking ModeTools
55.40
123 / 194

Text Embedding

1 evaluations
Benchmark / mode
Score
Rank/total
Context Arena
Thinking Mode
33.29
110 / 126

Productivity Knowledge

3 evaluations
Benchmark / mode
Score
Rank/total
GDPval-AA v2
Thinking ModeTools
1087
84 / 106
GDPval-AA
Thinking Mode
50
7 / 15
AA-AnalystAgent
Thinking ModeToolsInternet
11.25
24 / 29

Long Context

1 evaluations
Benchmark / mode
Score
Rank/total
AA-LCR
Thinking ModeTools
78.30
64 / 171

Claw-style Agent Evaluation

3 evaluations
Benchmark / mode
Score
Rank/total
Claw Bench
Thinking ModeTools
91.70
5 / 29
Pinch Bench
Thinking ModeTools
87.10
10 / 38
PinchBench v2
unknown
66.75
30 / 45

Multimodal Understanding

1 evaluations
Benchmark / mode
Score
Rank/total
GDP.pdf
Thinking Mode
6
92 / 119

Truthfulness Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
AA-Omniscience
unknown
0.80
43 / 44
View benchmark analysisCompare with other models

Compare with other models

MiniMax-M2.7

Publisher

MiniMax-M2.7

Model Overview

MiniMax-M2.7 is a reasoning model from MiniMaxAI, released on 2026-03-18.

It accepts text input and produces text output. Its cataloged capabilities include Reasoning model and Multilingual. The cataloged parameter count is 229B, with 10B active parameters per inference. The recorded context window is 200K, and the recorded maximum output is 200K.

The checkpoint is listed under the Minimax Modified Mit license, with the license link included in the model references. The page records 4 API pricing rules from MiniMaxAI; current provider pricing and conditions should be checked before deployment. The evaluation section contains 11 cataloged benchmark results with their recorded modes and scores. The page links 5 release, model-card, repository, or provider references for checking the underlying claims. Specifications, availability, and prices can change; undisclosed values are intentionally left unstated.

MiniMax-M2.7

FAQ

What is MiniMax-M2.7?

MiniMax-M2.7 is a reasoning model from MiniMaxAI, released on 2026-03-18. It accepts text input and returns text output. The cataloged parameter count is 229B, with 10B active parameters per inference. The recorded context window is 200K, and the recorded maximum output is 200K. Cataloged capabilities include Reasoning model and Multilingual. The checkpoint is listed under the Minimax Modified Mit license, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

What input and output modalities does MiniMax-M2.7 support?

The current model record lists text as input and text as output.

What are the main recorded specifications for MiniMax-M2.7?

The cataloged parameter count is 229B, with 10B active parameters per inference. The recorded context window is 200K, and the recorded maximum output is 200K. Fields without a source-backed value remain undisclosed.

Does MiniMax-M2.7 have API pricing?

The page records 4 API pricing rules from MiniMaxAI; current provider pricing and conditions should be checked before deployment.

Are benchmark results available for MiniMax-M2.7?

The evaluation section contains 11 cataloged benchmark results with their recorded modes and scores. Compare only results that use the same benchmark version and evaluation mode.

Is MiniMax-M2.7 open source?

The checkpoint is listed under the Minimax Modified Mit license, with the license link included in the model references. Review the linked license text before commercial or derivative use.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code