AIbase
EN
Home
AI Models Finder
Qwen3 32B (Reasoning)
Q

Qwen3 32B (Reasoning)

Qwen3-32B是阿里巴巴Qwen3系列的大型語言模型。它具有328億個參數，128k令牌上下文窗口，支持119種語言，以及允許在深度推理和快速響應之間切換的混合思維模式。它在推理、指令遵循和代理能力方面表現出色。
Intelligence(Medium)
Speed(Relatively Slow)
Input Supported Modalities
No
Is Reasoning Model
128,000
Context Window
128,000
Maximum Output Tokens
-
Knowledge Cutoff
Go Compare

Pricing

￥0.72 /M tokens
Input
￥2.16 /M tokens
Output
￥18.9 /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Qwen2.5 Turbo
Qwen Turbo
Wan2.2

Basic Parameters

Qwen3 32B (Reasoning)Technical Parameters
Parameter Count
32,800.0M
Context Length
128.00k tokens
Training Data Cutoff
Open Source Category
Open Weights (Permissive License)
Multimodal Support
Text Only
Throughput
327
Release Date
2025-04-28
Response Speed
59.7,644 tokens/s

Benchmark Scores

Below is the performance of Qwen3 32B (Reasoning) in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
59.16
Large Language Model Intelligence Level
Coding Index
45.01
Indicator of AI model performance on coding tasks
Math Index
88.37
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
79.8
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
66.8
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
8.3
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
54.6
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
35.4
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
96.1
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
80.7
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