通义千问2.0？文心一言媲美GPT-4？小小例子一较高下问题：百度文心一言：输出：阿里通义千问：输出： GPT-

问题：

百度文心一言：

<!DOCTYPE html>  
<html lang="en">  
<head>  
    <meta charset="UTF-8">  
    <meta http-equiv="X-UA-Compatible" content="IE=edge">  
    <meta name="viewport" content="width=device-width, initial-scale=1.0">  
    <title>Canvas L Shape</title>  
</head>  
<body>  
    <canvas id="myCanvas" width="500" height="500"></canvas>  
    <script>  
        const canvas = document.getElementById('myCanvas');  
        const ctx = canvas.getContext('2d');  
          
        ctx.beginPath();  
        ctx.moveTo(250, 0); // 设置起始点  
        ctx.lineTo(500, 500); // 绘制线条  
        ctx.stroke(); // 描边路径  
    </script>  
</body>  
</html>

输出：

阿里通义千问：

<!DOCTYPE html>
<html>

<body>

  <canvas id="myCanvas" width="300" height="150" style="border:1px solid #d3d3d3;">
    Your browser does not support the HTML5 canvas tag.
  </canvas>

  <script>
    var c = document.getElementById("myCanvas");
    var ctx = c.getContext("2d");

    // Set line color and width
    ctx.strokeStyle = "black";
    ctx.lineWidth = 2;

    // Draw horizontal line
    ctx.beginPath();
    ctx.moveTo(40, 75);
    ctx.lineTo(260, 75);
    ctx.stroke();

    // Draw vertical line
    ctx.beginPath();
    ctx.moveTo(150, 75);
    ctx.lineTo(150, 25);
    ctx.stroke();
  </script>

</body>

</html>

输出：

GPT-3.5

<!DOCTYPE html>
<html>
<head>
  <title>Canvas L Shape</title>
  <style>
    canvas {
      border: 1px solid black;
    }
  </style>
</head>
<body>
  <canvas id="myCanvas" width="200" height="200"></canvas>

  <script>
    // 获取Canvas元素
    var canvas = document.getElementById("myCanvas");
    var context = canvas.getContext("2d");

    // 绘制L形状
    context.beginPath();
    context.moveTo(50, 50);
    context.lineTo(50, 150);
    context.lineTo(150, 150);
    context.stroke();
  </script>
</body>
</html>

输出：

似乎国产的差点意思，不过已经很屌了，加油吧！