karimouda commited on
Commit
67d29c5
·
verified ·
1 Parent(s): aa64155

Add results file for Fanar-Prime

Browse files
results/QCRI/Fanar-Prime_results_2025-05-11_19-52-07.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "average_score": 6.982978723404256,
4
+ "speed": 15.632395428023747,
5
+ "contamination_score": 0,
6
+ "execution_time": 1421.279298,
7
+ "errors": [
8
+ {
9
+ "error": "('Connection aborted.', ConnectionResetError(54, 'Connection reset by peer'))",
10
+ "prompt": "{'role': 'user', 'content': \"\u0645\u0646 \u0647\u0648 \u0645\u0624\u0644\u0641 \u0647\u0630\u0647 \u0627\u0644\u0645\u0642\u0648\u0644\u0629 '\u0644\u0627 \u062a\u0633\u0623\u0644 \u0645\u0627\u0630\u0627 \u064a\u0645\u0643\u0646 \u0623\u0646 \u062a\u0641\u0639\u0644\u0647 \u0645\u0635\u0631 \u0644\u0643\u060c \u0628\u0644 \u0627\u0633\u0623\u0644 \u0645\u0627\u0630\u0627 \u064a\u0645\u0643\u0646\u0643 \u0623\u0646 \u062a\u0641\u0639\u0644\u0647 \u0644\u0645\u0635\u0631'\"}"
11
+ }
12
+ ],
13
+ "scores_by_category": [
14
+ {
15
+ "category": "Paraphrasing",
16
+ "average_score": 10.0,
17
+ "count": 6
18
+ },
19
+ {
20
+ "category": "Coding",
21
+ "average_score": 10.0,
22
+ "count": 3
23
+ },
24
+ {
25
+ "category": "Sentiment Analysis",
26
+ "average_score": 10.0,
27
+ "count": 9
28
+ },
29
+ {
30
+ "category": "Reading Comprehension",
31
+ "average_score": 8.823529411764707,
32
+ "count": 17
33
+ },
34
+ {
35
+ "category": "General Knowledge",
36
+ "average_score": 8.80952380952381,
37
+ "count": 63
38
+ },
39
+ {
40
+ "category": "MMLU",
41
+ "average_score": 8.429752066115702,
42
+ "count": 121
43
+ },
44
+ {
45
+ "category": "Function Calling",
46
+ "average_score": 7.666666666666667,
47
+ "count": 3
48
+ },
49
+ {
50
+ "category": "Long Context",
51
+ "average_score": 7.5,
52
+ "count": 4
53
+ },
54
+ {
55
+ "category": "Dialect Detection",
56
+ "average_score": 7.2727272727272725,
57
+ "count": 11
58
+ },
59
+ {
60
+ "category": "Summarization",
61
+ "average_score": 6.75,
62
+ "count": 8
63
+ },
64
+ {
65
+ "category": "RAG QA",
66
+ "average_score": 6.560975609756097,
67
+ "count": 41
68
+ },
69
+ {
70
+ "category": "Writing (incl Dialects)",
71
+ "average_score": 6.5,
72
+ "count": 22
73
+ },
74
+ {
75
+ "category": "Trust & Safety",
76
+ "average_score": 6.3,
77
+ "count": 30
78
+ },
79
+ {
80
+ "category": "Diacritization",
81
+ "average_score": 5.916666666666667,
82
+ "count": 12
83
+ },
84
+ {
85
+ "category": "Reasoning & Math",
86
+ "average_score": 5.488372093023256,
87
+ "count": 43
88
+ },
89
+ {
90
+ "category": "Entity Extraction",
91
+ "average_score": 4.6,
92
+ "count": 5
93
+ },
94
+ {
95
+ "category": "Hallucination",
96
+ "average_score": 4.333333333333333,
97
+ "count": 3
98
+ },
99
+ {
100
+ "category": "Translation (incl Dialects)",
101
+ "average_score": 4.25,
102
+ "count": 36
103
+ },
104
+ {
105
+ "category": "Arabic Language & Grammar",
106
+ "average_score": 3.4705882352941178,
107
+ "count": 17
108
+ },
109
+ {
110
+ "category": "Structuring",
111
+ "average_score": 3.3333333333333335,
112
+ "count": 3
113
+ },
114
+ {
115
+ "category": "Instruction Following",
116
+ "average_score": 3.0,
117
+ "count": 7
118
+ },
119
+ {
120
+ "category": "Transliteration",
121
+ "average_score": 0.5,
122
+ "count": 6
123
+ }
124
+ ],
125
+ "scores_by_format": [
126
+ {
127
+ "format": "Short Answer",
128
+ "average_score": 10.0,
129
+ "count": 5
130
+ },
131
+ {
132
+ "format": "MCQ",
133
+ "average_score": 8.017467248908297,
134
+ "count": 229
135
+ },
136
+ {
137
+ "format": "Generation",
138
+ "average_score": 5.991228070175438,
139
+ "count": 228
140
+ },
141
+ {
142
+ "format": "Fill-in-the-blank",
143
+ "average_score": 3.75,
144
+ "count": 8
145
+ }
146
+ ]
147
+ },
148
+ "config": {
149
+ "model": "QCRI/Fanar-Prime",
150
+ "model_sha": "na",
151
+ "submitted_time": "2025-05-11 19:28:13",
152
+ "likes": -1,
153
+ "params": 8.7,
154
+ "license": "closed",
155
+ "model_source": "API",
156
+ "model_category": "Small"
157
+ }
158
+ }