Minimax M1 80k

全球首個開源大規模混合注意力推理模型，總參數 456B，每 token 激活 45.9B 參數。採用 Lightning Attention 機制和 80K 思考預算，原生支援 1M token 上下文長度。在 AIME 2024 數學競賽中達到 86.0% 準確率，相比 DeepSeek R1 節省 75% 計算量，特別適合需要長輸入和深度思考的複雜任務。

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 80kTechnical 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

13.193,972 tokens/s

Benchmark Scores

Below is the performance of MiniMax M1 80k in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.

Intelligence Index

Large Language Model Intelligence Level

62.99

Large Language Model Intelligence Level

Coding Index

Indicator of AI model performance on coding tasks

54.25

Indicator of AI model performance on coding tasks

Math Index

Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks

91.33

Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks

MMLU Pro

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

81.6

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

GPQA

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

69.7

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

HLE

The model's comprehensive average score on the Hugging Face Open LLM Leaderboard

8.2

The model's comprehensive average score on the Hugging Face Open LLM Leaderboard

LiveCodeBench

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

71.1

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

SciCode

The model's capability in code generation for scientific computing or specific scientific domains

37.4

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

Score on the first 500 larger, more well-known mathematical benchmark tests

AIME Score

An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)

84.7

An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

131k

Context Length

Gemini 2.0 Flash Lite (Preview)

Output tokens/million

Output tokens/million

Output tokens/million

8192

Context Length

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご