AIbase
EN
Home
AI Models Finder
Minimax M1 40k
M

Minimax M1 40k

40K thinking budget version of MiniMax M1, providing good balance between performance and efficiency. Maintains 456B total parameter architecture and Lightning Attention mechanism, achieves 83.3% on AIME 2024 and 55.6% on SWE-bench Verified. Offers faster inference compared to 80K version, suitable for complex reasoning tasks with moderate response time requirements.
Intelligence(Relatively Strong)
Speed(Slow)
Input Supported Modalities
Yes
Is Reasoning Model
1,000,000
Context Window
-
Maximum Output Tokens
-
Knowledge Cutoff
Go Compare

Pricing

- /M tokens
Input
- /M tokens
Output
￥5.94 /M tokens
Blended Price

Quick Simple Comparison

Input

Output

MiniMax-Text-01
￥0.14
MiniMax-Text-01
MiniMax M1 40k

Basic Parameters

MiniMax M1 40kTechnical Parameters
Parameter Count
Not Announced
Context Length
1.0M tokens
Training Data Cutoff
Open Source Category
Open Weights (Permissive License)
Multimodal Support
Text Only
Throughput
Release Date
2025-06-17
Response Speed
12.075,414 tokens/s

Benchmark Scores

Below is the performance of MiniMax M1 40k in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
61.35
Large Language Model Intelligence Level
Coding Index
51.78
Indicator of AI model performance on coding tasks
Math Index
89.27
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
80.8
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
68.2
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
7.5
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
65.7
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
37.8
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
-
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
97.2
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
81.3
An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase