karimouda commited on
Commit
5fbd4a3
·
verified ·
1 Parent(s): 8bbc650

Add results file for gemini-2.0-flash

Browse files
results/google/gemini-2.0-flash_results_2025-05-11_11-23-14.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "average_score": 8.557446808510639,
4
+ "speed": 27.41952032338188,
5
+ "contamination_score": 0,
6
+ "execution_time": 939.586094,
7
+ "errors": [
8
+ {
9
+ "error": "[Errno 54] Connection reset by peer",
10
+ "prompt": "{'role': 'user', 'content': '\u0627\u0644\u0633\u0624\u0627\u0644 \u0627\u0644\u062a\u0627\u0644\u064a \u0647\u0648 \u0633\u0624\u0627\u0644 \u0645\u062a\u0639\u062f\u062f \u0627\u0644\u0625\u062e\u062a\u064a\u0627\u0631\u0627\u062a. \u0627\u062e\u062a\u0631 \u0627\u0644\u0625\u062c\u0627\u0628\u0629 \u0627\u0644\u0635\u062d\u064a\u062d\u0629:\\n\\n.\u0642\u0627\u0644 \u0627\u0644\u0631\u0633\u0648\u0644 \u0635\u0644\u0649 \u0627\u0644\u0644\u0647 \u0639\u0644\u064a\u0647 \u0648\u0633\u0644\u0645:(\u0645\u0646 \u0634\u0647\u062f \u0627\u0644\u062c\u0646\u0627\u0632\u0629 \u062d\u062a\u0649 \u064a\u0635\u0644\u0649 \u0639\u0644\u064a\u0647\u0627 \u0641\u0644\u0647 \u0642\u064a\u0631\u0627\u0637 \u0648\u0645\u0646 \u0634\u0647\u062f\u0647\u0627 \u062d\u062a\u0649 \u062a\u062f\u0641\u0646 \u0641\u0644\u0647:\\n\u0623. \u0642\u064a\u0631\u0627\u0637\u0627\u0646\\n\u0628. 3 \u0623\u0642\u0631\u0627\u0637\\n\u062c. \u0642\u064a\u0631\u0627\u0637\\n\u062f. 4 \u0623\u0642\u0631\u0627\u0637\\n\u0627\u0643\u062a\u0628 \u0627\u0644\u0625\u062c\u0627\u0628\u0629 \u0643\u0645\u0627 \u0647\u064a \u0645\u0646 \u0627\u0644\u0627\u062e\u062a\u064a\u0627\u0631\u0627\u062a \u062f\u0648\u0646 \u0634\u0631\u062d:'}"
11
+ }
12
+ ],
13
+ "scores_by_category": [
14
+ {
15
+ "category": "Paraphrasing",
16
+ "average_score": 10.0,
17
+ "count": 6
18
+ },
19
+ {
20
+ "category": "Hallucination",
21
+ "average_score": 10.0,
22
+ "count": 3
23
+ },
24
+ {
25
+ "category": "Coding",
26
+ "average_score": 10.0,
27
+ "count": 3
28
+ },
29
+ {
30
+ "category": "Diacritization",
31
+ "average_score": 9.666666666666666,
32
+ "count": 12
33
+ },
34
+ {
35
+ "category": "Reading Comprehension",
36
+ "average_score": 9.411764705882353,
37
+ "count": 17
38
+ },
39
+ {
40
+ "category": "General Knowledge",
41
+ "average_score": 9.317460317460318,
42
+ "count": 63
43
+ },
44
+ {
45
+ "category": "MMLU",
46
+ "average_score": 9.173553719008265,
47
+ "count": 121
48
+ },
49
+ {
50
+ "category": "Long Context",
51
+ "average_score": 9.0,
52
+ "count": 4
53
+ },
54
+ {
55
+ "category": "Trust & Safety",
56
+ "average_score": 8.666666666666666,
57
+ "count": 30
58
+ },
59
+ {
60
+ "category": "Function Calling",
61
+ "average_score": 8.666666666666666,
62
+ "count": 3
63
+ },
64
+ {
65
+ "category": "Entity Extraction",
66
+ "average_score": 8.6,
67
+ "count": 5
68
+ },
69
+ {
70
+ "category": "Reasoning & Math",
71
+ "average_score": 8.534883720930232,
72
+ "count": 43
73
+ },
74
+ {
75
+ "category": "Summarization",
76
+ "average_score": 8.375,
77
+ "count": 8
78
+ },
79
+ {
80
+ "category": "Transliteration",
81
+ "average_score": 8.166666666666666,
82
+ "count": 6
83
+ },
84
+ {
85
+ "category": "RAG QA",
86
+ "average_score": 8.0,
87
+ "count": 41
88
+ },
89
+ {
90
+ "category": "Writing (incl Dialects)",
91
+ "average_score": 7.954545454545454,
92
+ "count": 22
93
+ },
94
+ {
95
+ "category": "Sentiment Analysis",
96
+ "average_score": 7.777777777777778,
97
+ "count": 9
98
+ },
99
+ {
100
+ "category": "Translation (incl Dialects)",
101
+ "average_score": 7.666666666666667,
102
+ "count": 36
103
+ },
104
+ {
105
+ "category": "Arabic Language & Grammar",
106
+ "average_score": 6.882352941176471,
107
+ "count": 17
108
+ },
109
+ {
110
+ "category": "Dialect Detection",
111
+ "average_score": 6.090909090909091,
112
+ "count": 11
113
+ },
114
+ {
115
+ "category": "Instruction Following",
116
+ "average_score": 5.714285714285714,
117
+ "count": 7
118
+ },
119
+ {
120
+ "category": "Structuring",
121
+ "average_score": 2.6666666666666665,
122
+ "count": 3
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": 8.925764192139738,
134
+ "count": 229
135
+ },
136
+ {
137
+ "format": "Fill-in-the-blank",
138
+ "average_score": 8.75,
139
+ "count": 8
140
+ },
141
+ {
142
+ "format": "Generation",
143
+ "average_score": 8.149122807017545,
144
+ "count": 228
145
+ }
146
+ ]
147
+ },
148
+ "config": {
149
+ "model": "google/gemini-2.0-flash",
150
+ "model_sha": "na",
151
+ "submitted_time": "2025-05-11 11:07:28",
152
+ "likes": -1,
153
+ "params": 999,
154
+ "license": "closed",
155
+ "model_source": "API",
156
+ "model_category": "Large"
157
+ }
158
+ }