karimouda commited on
Commit
7f9acf8
·
verified ·
1 Parent(s): d432b7f

Delete results/openai/gpt-4.1-nano_results_2025-04-28_21-12-26.json

Browse files
results/openai/gpt-4.1-nano_results_2025-04-28_21-12-26.json DELETED
@@ -1,153 +0,0 @@
1
- {
2
- "results": {
3
- "average_score": 8.040860215053764,
4
- "speed": 1.8531926430107528,
5
- "contamination_score": -0.021933454541668063,
6
- "execution_time": 861.734579,
7
- "errors": [],
8
- "scores_by_category": [
9
- {
10
- "category": "Paraphrasing",
11
- "average_score": 10.0,
12
- "count": 6
13
- },
14
- {
15
- "category": "Coding",
16
- "average_score": 10.0,
17
- "count": 3
18
- },
19
- {
20
- "category": "Writing (incl Dialects)",
21
- "average_score": 9.727272727272727,
22
- "count": 22
23
- },
24
- {
25
- "category": "RAG QA",
26
- "average_score": 9.523809523809524,
27
- "count": 21
28
- },
29
- {
30
- "category": "Sentiment Analysis",
31
- "average_score": 8.88888888888889,
32
- "count": 9
33
- },
34
- {
35
- "category": "Summarization",
36
- "average_score": 8.666666666666666,
37
- "count": 9
38
- },
39
- {
40
- "category": "MMLU",
41
- "average_score": 8.442622950819672,
42
- "count": 122
43
- },
44
- {
45
- "category": "Translation (incl Dialects)",
46
- "average_score": 8.386363636363637,
47
- "count": 44
48
- },
49
- {
50
- "category": "Instruction Following",
51
- "average_score": 8.0,
52
- "count": 7
53
- },
54
- {
55
- "category": "Diacritization",
56
- "average_score": 8.0,
57
- "count": 12
58
- },
59
- {
60
- "category": "Entity Extraction",
61
- "average_score": 8.0,
62
- "count": 5
63
- },
64
- {
65
- "category": "General Knowledge",
66
- "average_score": 7.865671641791045,
67
- "count": 67
68
- },
69
- {
70
- "category": "Reading Comprehension",
71
- "average_score": 7.647058823529412,
72
- "count": 17
73
- },
74
- {
75
- "category": "Reasoning & Math",
76
- "average_score": 7.465116279069767,
77
- "count": 43
78
- },
79
- {
80
- "category": "Transliteration",
81
- "average_score": 7.166666666666667,
82
- "count": 6
83
- },
84
- {
85
- "category": "Trust & Safety",
86
- "average_score": 7.033333333333333,
87
- "count": 30
88
- },
89
- {
90
- "category": "Function Calling",
91
- "average_score": 7.0,
92
- "count": 3
93
- },
94
- {
95
- "category": "Arabic Language & Grammar",
96
- "average_score": 6.9411764705882355,
97
- "count": 17
98
- },
99
- {
100
- "category": "Hallucination",
101
- "average_score": 6.666666666666667,
102
- "count": 3
103
- },
104
- {
105
- "category": "Dialect Detection",
106
- "average_score": 5.545454545454546,
107
- "count": 11
108
- },
109
- {
110
- "category": "Structuring",
111
- "average_score": 4.666666666666667,
112
- "count": 3
113
- },
114
- {
115
- "category": "Long Context",
116
- "average_score": 4.0,
117
- "count": 5
118
- }
119
- ],
120
- "scores_by_format": [
121
- {
122
- "format": "Generation",
123
- "average_score": 8.48165137614679,
124
- "count": 218
125
- },
126
- {
127
- "format": "Short Answer",
128
- "average_score": 8.0,
129
- "count": 5
130
- },
131
- {
132
- "format": "MCQ",
133
- "average_score": 7.6923076923076925,
134
- "count": 234
135
- },
136
- {
137
- "format": "Fill-in-the-blank",
138
- "average_score": 6.25,
139
- "count": 8
140
- }
141
- ]
142
- },
143
- "config": {
144
- "model": "openai/gpt-4.1-nano",
145
- "model_sha": "NA",
146
- "submitted_time": "2025-04-28 20:57:22",
147
- "likes": -1,
148
- "params": 999,
149
- "license": "closed",
150
- "model_source": "API",
151
- "model_category": "Large"
152
- }
153
- }