QwQ 32B Preview
Discover QwQ-32B Preview, Alibaba's groundbreaking 32B open-source reasoning model that outperforms OpenAI's o1 on math benchmarks like AIME (50%) and MATH-500 (90.6%), delivering step-by-step test-time compute for superior problem-solving in coding, logic, and science. Experience this experimental powerhouse on SambaNova Cloud, optimized for 3x faster inference with an 8K context length.
Available for Chat, Vision, and File Uploads.
Performance Benchmarks
How do you want to interact?
Start a Conversation
Ask anything.
Have a natural conversation, brainstorm ideas, draft emails, or ask for advice.
Use a Persona
Specialized Experts.
Instruct the AI to act as a Coding Tutor, Marketing Expert, or Travel Guide.
Why use QwQ 32B Preview?
Advanced Reasoning
Performs multi-step reasoning with self-questioning, introspection, and meta-cognitive processes for nuanced, human-like problem-solving
Extended Context Length
Supports 32,768 tokens to maintain coherence in complex tasks and process large inputs
High Benchmark Performance
Excels in math (MATH-500: 90.6%, AIME: 50.0%), coding (LiveCodeBench: 50.0%), and science (GPQA: 65.2%)
Capability Examples
Math Reasoning Challenge
Coding Task
How to use
Go to Chat
Navigate to the "AI Chat" page.
Select Model
Ensure QwQ 32B Preview is selected.
Type Prompt
Ask a question or paste code.
Interact
Refine the answer by replying to the AI.
Compare LLMs Side-by-Side
Is QwQ 32B Preview better than Claude 3.5 or Gemini? Test same prompts simultaneously in the Chat Playground.
Open Chat PlaygroundMade with ❤ by AI4Chat