AIbase
EN
Home
AI Models Finder
Qwen2.5 Max
Q

Qwen2.5 Max

Largest version of Alibaba's Qwen2.5 series, representing top-tier performance of the series. Features powerful multilingual capabilities with exceptional Chinese understanding and generation. Max version means highest parameter scale and strongest capabilities, suitable for applications requiring complex Chinese task processing, cross-language understanding, and high-quality content generation, providing top-tier solutions for Chinese AI applications.
Intelligence(Medium)
Speed(Slow)
Input Supported Modalities
Yes
Is Reasoning Model
32,000
Context Window
-
Maximum Output Tokens
-
Knowledge Cutoff
Go Compare

Pricing

- /M tokens
Input
- /M tokens
Output
￥20.16 /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Qwen2.5 Turbo
Qwen Turbo
Wan2.2

Basic Parameters

Qwen2.5 MaxTechnical Parameters
Parameter Count
Not Announced
Context Length
32.00k tokens
Training Data Cutoff
Open Source Category
Proprietary
Multimodal Support
Text Only
Throughput
Release Date
2025-01-28
Response Speed
39.785,748 tokens/s

Benchmark Scores

Below is the performance of Qwen2.5 Max in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
45.28
Large Language Model Intelligence Level
Coding Index
34.78
Indicator of AI model performance on coding tasks
Math Index
53.4
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
76.2
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
58.7
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
4.5
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
35.9
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
33.7
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
92.9
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
83.5
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
23.3
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