karimouda commited on
Commit
0a2a5ad
·
verified ·
1 Parent(s): 2e05c0b

Add results file for claude-3-7-sonnet-20250219

Browse files
results/anthropic/claude-3-7-sonnet-20250219_results_2025-05-11_17-46-22.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "average_score": 8.912765957446808,
4
+ "speed": 3.128823906158828,
5
+ "contamination_score": 0,
6
+ "execution_time": 5692.873915,
7
+ "errors": [],
8
+ "scores_by_category": [
9
+ {
10
+ "category": "Paraphrasing",
11
+ "average_score": 10.0,
12
+ "count": 6
13
+ },
14
+ {
15
+ "category": "Sentiment Analysis",
16
+ "average_score": 10.0,
17
+ "count": 9
18
+ },
19
+ {
20
+ "category": "Hallucination",
21
+ "average_score": 10.0,
22
+ "count": 3
23
+ },
24
+ {
25
+ "category": "Long Context",
26
+ "average_score": 10.0,
27
+ "count": 4
28
+ },
29
+ {
30
+ "category": "Coding",
31
+ "average_score": 10.0,
32
+ "count": 3
33
+ },
34
+ {
35
+ "category": "Reading Comprehension",
36
+ "average_score": 10.0,
37
+ "count": 17
38
+ },
39
+ {
40
+ "category": "MMLU",
41
+ "average_score": 9.834710743801653,
42
+ "count": 121
43
+ },
44
+ {
45
+ "category": "Instruction Following",
46
+ "average_score": 9.714285714285714,
47
+ "count": 7
48
+ },
49
+ {
50
+ "category": "Diacritization",
51
+ "average_score": 9.333333333333334,
52
+ "count": 12
53
+ },
54
+ {
55
+ "category": "General Knowledge",
56
+ "average_score": 9.238095238095237,
57
+ "count": 63
58
+ },
59
+ {
60
+ "category": "Dialect Detection",
61
+ "average_score": 9.0,
62
+ "count": 11
63
+ },
64
+ {
65
+ "category": "Trust & Safety",
66
+ "average_score": 9.0,
67
+ "count": 30
68
+ },
69
+ {
70
+ "category": "Summarization",
71
+ "average_score": 9.0,
72
+ "count": 8
73
+ },
74
+ {
75
+ "category": "Entity Extraction",
76
+ "average_score": 8.8,
77
+ "count": 5
78
+ },
79
+ {
80
+ "category": "Reasoning & Math",
81
+ "average_score": 8.604651162790697,
82
+ "count": 43
83
+ },
84
+ {
85
+ "category": "Arabic Language & Grammar",
86
+ "average_score": 8.058823529411764,
87
+ "count": 17
88
+ },
89
+ {
90
+ "category": "Transliteration",
91
+ "average_score": 8.0,
92
+ "count": 6
93
+ },
94
+ {
95
+ "category": "Translation (incl Dialects)",
96
+ "average_score": 7.666666666666667,
97
+ "count": 36
98
+ },
99
+ {
100
+ "category": "RAG QA",
101
+ "average_score": 7.634146341463414,
102
+ "count": 41
103
+ },
104
+ {
105
+ "category": "Writing (incl Dialects)",
106
+ "average_score": 7.454545454545454,
107
+ "count": 22
108
+ },
109
+ {
110
+ "category": "Function Calling",
111
+ "average_score": 5.0,
112
+ "count": 3
113
+ },
114
+ {
115
+ "category": "Structuring",
116
+ "average_score": 3.0,
117
+ "count": 3
118
+ }
119
+ ],
120
+ "scores_by_format": [
121
+ {
122
+ "format": "Short Answer",
123
+ "average_score": 10.0,
124
+ "count": 5
125
+ },
126
+ {
127
+ "format": "MCQ",
128
+ "average_score": 9.554585152838428,
129
+ "count": 229
130
+ },
131
+ {
132
+ "format": "Fill-in-the-blank",
133
+ "average_score": 8.75,
134
+ "count": 8
135
+ },
136
+ {
137
+ "format": "Generation",
138
+ "average_score": 8.25,
139
+ "count": 228
140
+ }
141
+ ]
142
+ },
143
+ "config": {
144
+ "model": "anthropic/claude-3-7-sonnet-20250219",
145
+ "model_sha": "na",
146
+ "submitted_time": "2025-05-11 16:11:22",
147
+ "likes": -1,
148
+ "params": 999,
149
+ "license": "closed",
150
+ "model_source": "API",
151
+ "model_category": "Large"
152
+ }
153
+ }