Add responses file for gpt-3.5-turbo
Browse files
results/open-ai/gpt-3.5-turbo_abb_benchmark_answers_2025-04-25 16:40:03.923150+00:00.html
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
<!DOCTYPE html>
|
| 3 |
+
<html lang="ar" dir="rtl">
|
| 4 |
+
<head>
|
| 5 |
+
<meta charset="UTF-8">
|
| 6 |
+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
| 7 |
+
<title>Arabic Broad Benchmark Results</title>
|
| 8 |
+
<style>
|
| 9 |
+
body {
|
| 10 |
+
font-family: Arial, sans-serif;
|
| 11 |
+
direction: rtl;
|
| 12 |
+
text-align: right;
|
| 13 |
+
}
|
| 14 |
+
table {
|
| 15 |
+
border-collapse: collapse;
|
| 16 |
+
width: 100%;
|
| 17 |
+
}
|
| 18 |
+
th, td {
|
| 19 |
+
border: 1px solid #ddd;
|
| 20 |
+
padding: 8px;
|
| 21 |
+
white-space: break-spaces;
|
| 22 |
+
}
|
| 23 |
+
th {
|
| 24 |
+
background-color: #f2f2f2;
|
| 25 |
+
}
|
| 26 |
+
tr:nth-child(even) {
|
| 27 |
+
background-color: #f9f9f9;
|
| 28 |
+
}
|
| 29 |
+
tr:hover {
|
| 30 |
+
background-color: #ddd;
|
| 31 |
+
}
|
| 32 |
+
</style>
|
| 33 |
+
</head>
|
| 34 |
+
<body>
|
| 35 |
+
<h1>Arabic Broad Benchmark Results</h1>
|
| 36 |
+
<table border="1" class="dataframe">
|
| 37 |
+
<thead>
|
| 38 |
+
<tr style="text-align: right;">
|
| 39 |
+
<th></th>
|
| 40 |
+
<th>source</th>
|
| 41 |
+
<th>category</th>
|
| 42 |
+
<th>subcategory</th>
|
| 43 |
+
<th>format</th>
|
| 44 |
+
<th>prediction</th>
|
| 45 |
+
<th>reference</th>
|
| 46 |
+
<th>score</th>
|
| 47 |
+
</tr>
|
| 48 |
+
</thead>
|
| 49 |
+
<tbody>
|
| 50 |
+
<tr>
|
| 51 |
+
<th>0</th>
|
| 52 |
+
<td>silma-folk-riddles</td>
|
| 53 |
+
<td>Reasoning & Math</td>
|
| 54 |
+
<td>Riddles</td>
|
| 55 |
+
<td>Generation</td>
|
| 56 |
+
<td>إذا كان لديها ثلاثة أبناء فلا يوجد ابن رابع، لذا لا يمكن معرفة اسم ابنها الرابع.</td>
|
| 57 |
+
<td>اسم ابنها الرابع هو "محمد"، حيث أن السؤال يبدأ بعبارة "ام محمد"، مما يشير إلى أن لديها ابنًا اسمه محمد.</td>
|
| 58 |
+
<td>1</td>
|
| 59 |
+
</tr>
|
| 60 |
+
<tr>
|
| 61 |
+
<th>1</th>
|
| 62 |
+
<td>silma-folk-riddles</td>
|
| 63 |
+
<td>Reasoning & Math</td>
|
| 64 |
+
<td>Riddles</td>
|
| 65 |
+
<td>Generation</td>
|
| 66 |
+
<td>يوجد حرف الفاء مرتين في كلمة "ذلك".</td>
|
| 67 |
+
<td>لا يوجد أي حرف "فاء" في كلمة "ذلك".</td>
|
| 68 |
+
<td>1</td>
|
| 69 |
+
</tr>
|
| 70 |
+
<tr>
|
| 71 |
+
<th>2</th>
|
| 72 |
+
<td>silma-folk-riddles</td>
|
| 73 |
+
<td>Reasoning & Math</td>
|
| 74 |
+
<td>Riddles</td>
|
| 75 |
+
<td>Generation</td>
|
| 76 |
+
<td>انا بوت ذكاء اصطناعي ولا امتلك علاقات عائلية. كيف يمكنني مساعدتك اليوم؟</td>
|
| 77 |
+
<td>الإجابة هي: أنت.</td>
|
| 78 |
+
<td>2</td>
|
| 79 |
+
</tr>
|
| 80 |
+
</tbody>
|
| 81 |
+
</table>
|
| 82 |
+
</body>
|
| 83 |
+
</html>
|
| 84 |
+
|