Add results file for o3
Browse files
results/openai/o3_results_2025-05-23_08-49-13.json
ADDED
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": {
|
3 |
+
"average_score": 8.961702127659574,
|
4 |
+
"speed": 4.236624114787222,
|
5 |
+
"contamination_score": 0,
|
6 |
+
"execution_time": 5196.826389,
|
7 |
+
"errors": [
|
8 |
+
{
|
9 |
+
"error": "Error code: 400 - {'error': {'message': 'Invalid prompt: your prompt was flagged as potentially violating our usage policy. Please try again with a different prompt: https://platform.openai.com/docs/guides/reasoning#advice-on-prompting', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_prompt'}}",
|
10 |
+
"prompt": "{'role': 'user', 'content': '\u0644\u062f\u064a\u0643 \u062b\u0644\u0627\u062b\u0629 \u0635\u0646\u0627\u062f\u064a\u0642 \u0627\u0644\u0623\u0648\u0644\u0649 \u062a\u062d\u062a\u0648\u064a \u0639\u0644\u0649 \u0643\u0631\u0627\u062a \u062d\u0645\u0631\u0627\u0621 \u0641\u0642\u0637 \u0648\u0627\u0644\u062b\u0627\u0646\u064a\u0629 \u062a\u062d\u062a\u0648\u064a \u0639\u0644\u0649 \u0643\u0631\u0627\u062a \u0632\u0631\u0642\u0627\u0621 \u0641\u0642\u0637 \u0648\u0627\u0644\u062b\u0627\u0644\u062b\u0629 \u062a\u062d\u062a\u0648\u064a \u0639\u0644\u0649 \u0645\u0632\u064a\u062c \u0645\u0646 \u0627\u0644\u0643\u0631\u0627\u062a \u0627\u0644\u062d\u0645\u0631\u0627\u0621 \u0648\u0627\u0644\u0632\u0631\u0642\u0627\u0621 \u062c\u0645\u064a\u0639 \u0627\u0644\u0635\u0646\u0627\u062f\u064a\u0642 \u062a\u0645 \u062a\u0633\u0645\u064a\u062a\u0647\u0627 \u0628\u0634\u0643\u0644 \u062e\u0627\u0637\u0626 \u0643\u064a\u0641 \u064a\u0645\u0643\u0646\u0643 \u062a\u0635\u062d\u064a\u062d \u0627\u0644\u062a\u0633\u0645\u064a\u0627\u062a \u0628\u0633\u062d\u0628 \u0643\u0631\u0629 \u0648\u0627\u062d\u062f\u0629 \u0641\u0642\u0637 \u0645\u0646 \u0625\u062d\u062f\u0649 \u0627\u0644\u0635\u0646\u0627\u062f\u064a\u0642'}"
|
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": 10.0,
|
32 |
+
"count": 17
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"category": "Long Context",
|
36 |
+
"average_score": 10.0,
|
37 |
+
"count": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"category": "MMLU",
|
41 |
+
"average_score": 9.50413223140496,
|
42 |
+
"count": 121
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"category": "General Knowledge",
|
46 |
+
"average_score": 9.444444444444445,
|
47 |
+
"count": 63
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"category": "Trust & Safety",
|
51 |
+
"average_score": 9.333333333333334,
|
52 |
+
"count": 30
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"category": "RAG QA",
|
56 |
+
"average_score": 9.21951219512195,
|
57 |
+
"count": 41
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"category": "Reasoning & Math",
|
61 |
+
"average_score": 8.837209302325581,
|
62 |
+
"count": 43
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"category": "Diacritization",
|
66 |
+
"average_score": 8.833333333333334,
|
67 |
+
"count": 12
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"category": "Entity Extraction",
|
71 |
+
"average_score": 8.8,
|
72 |
+
"count": 5
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"category": "Instruction Following",
|
76 |
+
"average_score": 8.714285714285714,
|
77 |
+
"count": 7
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"category": "Transliteration",
|
81 |
+
"average_score": 8.5,
|
82 |
+
"count": 6
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"category": "Function Calling",
|
86 |
+
"average_score": 8.0,
|
87 |
+
"count": 3
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"category": "Dialect Detection",
|
91 |
+
"average_score": 8.0,
|
92 |
+
"count": 11
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"category": "Translation (incl Dialects)",
|
96 |
+
"average_score": 7.722222222222222,
|
97 |
+
"count": 36
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"category": "Structuring",
|
101 |
+
"average_score": 7.666666666666667,
|
102 |
+
"count": 3
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"category": "Writing (incl Dialects)",
|
106 |
+
"average_score": 7.545454545454546,
|
107 |
+
"count": 22
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"category": "Summarization",
|
111 |
+
"average_score": 7.375,
|
112 |
+
"count": 8
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"category": "Arabic Language & Grammar",
|
116 |
+
"average_score": 7.0,
|
117 |
+
"count": 17
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"category": "Hallucination",
|
121 |
+
"average_score": 6.666666666666667,
|
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": 9.397379912663755,
|
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": 8.508771929824562,
|
144 |
+
"count": 228
|
145 |
+
}
|
146 |
+
]
|
147 |
+
},
|
148 |
+
"config": {
|
149 |
+
"model": "openai/o3",
|
150 |
+
"model_sha": "na",
|
151 |
+
"submitted_time": "2025-05-23 07:22:31",
|
152 |
+
"likes": -1,
|
153 |
+
"params": 999,
|
154 |
+
"license": "closed",
|
155 |
+
"model_source": "API",
|
156 |
+
"model_category": "Large"
|
157 |
+
}
|
158 |
+
}
|