DataLearner logo
MI

MiniMax M2.5

Reasoning modelMiniMax MMiniMax M2.5

MiniMax M2.5

Release date: 2026-02-12Updated: 2026-04-12 13:57:12.4636,561
Parameters
229B
Context length
128K
Chinese support
Supported
Reasoning ability

MiniMax M2.5 is an AI model published by MiniMaxAI, released on 2026-02-12, for Reasoning model, with 229B parameters, and 128K context length, requiring about 230GB storage, under the MINIMAX MODEL LICENSE license, with a 97.80 score on τ²-Bench - Telecom.

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

MiniMax M2.5

Model basics

Reasoning traces
Supported
Thinking modes
Thinking Mode (Default)Standard Mode
Context length
128K tokens
Max output length
No data
Model type
Reasoning model
Modality (in / out)
No data
Release date
2026-02-12
Model file size
230GB
MoE architecture
Yes
Total params / Active params
229B / 10B
Knowledge cutoff
No data
MiniMax M2.5

Open source & experience

MiniMax M2.5

Official resources

DataLearnerAI blog
No blog post yet
MiniMax M2.5

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$0.300/ 1M$2.40/ 1M
Turbo
TypeConditionInputOutput
Text-$0.150/ 1M$1.20/ 1M
MiniMax M2.5

Benchmark Results

MiniMax M2.5 currently shows benchmark results led by SWE-bench Verified (13 / 109, score 80.20), Claw Bench (4 / 29, score 92.10), Pinch Bench (6 / 37, score 87.80). 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

General Knowledge

5 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Thinking Mode
85.20
50 / 180
ARC-AGI
Thinking Mode
63.70
32 / 65
60.14
68 / 115
HLE
Thinking Mode
19.40
113 / 164
ARC-AGI-2
Thinking Mode
4.90
44 / 59

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Thinking Mode
86.30
48 / 106

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
70
12 / 29

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
76.30
20 / 49

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total
51.70
30 / 46

Productivity Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
GDPval-AA
Thinking Mode
36
17 / 21

Long Context

1 evaluations
Benchmark / mode
Score
Rank/total
AA-LCR
Thinking Mode
69.50
4 / 14

Claw-style Agent Evaluation

2 evaluations
Benchmark / mode
Score
Rank/total
Claw Bench
Thinking ModeTools
92.10
4 / 29
Pinch Bench
Thinking ModeTools
87.80
6 / 37

Compare with other models

MiniMax M2.5

Publisher

MiniMax M2.5

Model Overview

MiniMax M2.5 is an AI model published by MiniMaxAI, released on 2026-02-12, for Reasoning model, with 229B parameters, and 128K context length, requiring about 230GB storage, under the MINIMAX MODEL LICENSE license, with a 97.80 score on τ²-Bench - Telecom.

DataLearner on WeChat

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

DataLearner WeChat QR code