AIbase
EN
Home
AI Models Finder
Qwen2.5 Turbo
Q

Qwen2.5 Turbo

High-speed version of Alibaba's Qwen2.5 series, optimizing inference speed while maintaining powerful capabilities. Turbo version designed for applications requiring fast response, excelling in Chinese understanding, multilingual processing, and real-time conversation. Suitable for customer service, real-time translation, fast content generation and other applications requiring efficient response, providing high-speed AI solutions for Chinese market.
Intelligence(Relatively Weak)
Speed(Relatively 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
￥0.63 /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Qwen2.5 Turbo
Qwen Turbo
Wan2.2

Basic Parameters

Qwen2.5 TurboTechnical Parameters
Parameter Count
Not Announced
Context Length
1.0M tokens
Training Data Cutoff
Open Source Category
Proprietary
Multimodal Support
Text Only
Throughput
Release Date
2024-11-18
Response Speed
91.413,826 tokens/s

Benchmark Scores

Below is the performance of Qwen2.5 Turbo in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
33.6
Large Language Model Intelligence Level
Coding Index
15.79
Indicator of AI model performance on coding tasks
Math Index
46.27
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
63.3
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
41
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
4.2
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
16.3
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
15.3
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
84.6
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
80.5
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
12
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