阿里发布最新推理模型QwQ-32B，性能比肩全球最强开源推理模型

开源地址：

Qwen Chat免费体验：

https://chat.qwen.ai/?models=Qwen2.5-Plus

模型效果

可以看到，QwQ-32B 的表现非常出色，在 LiveBench、IFEval 和 BFCL 基准上甚至略微超过了 DeepSeek-R1-671B。

在第一阶段的 RL 过后，他们又增加了另一个针对通用能力的 RL。此阶段使用通用奖励模型和一些基于规则的验证器进行训练。结果发现，通过少量步骤的通用 RL，可以提升其他通用能力，同时在数学和编程任务上的性能没有显著下降。

from openai import OpenAI
import os

# Initialize OpenAI client
client = OpenAI(
    # If the environment variable is not configured, replace with your API Key: api_key="sk-xxx"    
    # How to get an API Key：https://help.aliyun.com/zh/model-studio/developer-reference/get-api-key    
    api_key=os.getenv("DASHSCOPE_API_KEY"),    
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
)

reasoning_content = ""
content = ""

is_answering = False

completion = client.chat.completions.create(
    model="qwq-32b",    
    messages=[
            {"role": "user", "content": "Which is larger, 9.9 or 9.11?"}    
            ],    
            stream=True,    
            # Uncomment the following line to return token usage in the last chunk    
            # stream_options={    
            #     "include_usage": True    
            # }
)
print("\n" + "=" * 20 + "reasoning content" + "=" * 20 + "\n")

for chunk in completion:    
      # If chunk.choices is empty, print usage
      if not chunk.choices:        
          print("\nUsage:")        
          print(chunk.usage)    
      else:        
        delta = chunk.choices[0].delta
        # Print reasoning content        
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content is not None:            
           print(delta.reasoning_content, end='', flush=True)            
           reasoning_content += delta.reasoning_content        
        else:            
           if delta.content != "" and is_answering is False:                
              print("\n" + "=" * 20 + "content" + "=" * 20 + "\n")                
              is_answering = True            
        # Print content            
        print(delta.content, end='', flush=True)            
        content += delta.conten