AIbase
EN
Home
AI Models Finder
Qwen2.5 Instruct 32B
Q

Qwen2.5 Instruct 32B

Qwen2.5-32B-Instruct is an instruction-tuned language model with 32 billion parameters and is part of the Qwen2.5 series. It is designed to follow instructions, generate long text (over 8K tokens), understand structured data (such as tables), and generate structured outputs, especially JSON. The model supports multilingual capabilities in over 29 languages.
Intelligence(Relatively Weak)
Speed(Slow)
Input Supported Modalities
No
Is Reasoning Model
128,000
Context Window
8,192
Maximum Output Tokens
-
Knowledge Cutoff
Go Compare

Pricing

- /M tokens
Input
- /M tokens
Output
￥1.05 /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Qwen2.5 Turbo
Qwen Turbo
Wan2.2

Basic Parameters

Qwen2.5 Instruct 32BTechnical Parameters
Parameter Count
32,500.0M
Context Length
128.00k tokens
Training Data Cutoff
Open Source Category
Open Weights (Permissive License)
Multimodal Support
Text Only
Throughput
0
Release Date
2024-09-19
Response Speed
0 tokens/s

Benchmark Scores

Below is the performance of Qwen2.5 Instruct 32B in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
37.41
Large Language Model Intelligence Level
Coding Index
23.84
Indicator of AI model performance on coding tasks
Math Index
45.77
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
69.7
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
46.6
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
3.8
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
24.8
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
22.9
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
90
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
11
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