Delete results/openai/o3_results_2025-05-11_19-13-35.json
Browse files
results/openai/o3_results_2025-05-11_19-13-35.json
DELETED
@@ -1,158 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"results": {
|
3 |
-
"average_score": 7.727659574468085,
|
4 |
-
"speed": 2.9113119225076014,
|
5 |
-
"contamination_score": 0,
|
6 |
-
"execution_time": 3119.89929,
|
7 |
-
"errors": [
|
8 |
-
{
|
9 |
-
"error": "Error code: 400 - {'error': {'message': 'Could not finish the message because max_tokens or model output limit was reached. Please try again with higher max_tokens.', 'type': 'invalid_request_error', 'param': None, 'code': None}}",
|
10 |
-
"prompt": "{'role': 'user', 'content': \"\u0627\u0643\u062a\u0628 \u0645\u0646\u0634\u0648\u0631 \u0639\u0644\u0649 \u0627\u0644\u0641\u064a\u0633\u0628\u0648\u0643 \u0639\u0646 \u0627\u0644\u0633\u0648\u0642 \u0627\u0644\u0634\u0639\u0628\u064a \u0628\u0635\u064a\u063a\u0629 JSON. \u0644\u0627 \u062a\u0630\u0643\u0631 \u0627\u0644\u0643\u0644\u0645\u0627\u062a \u0627\u0644\u062a\u0627\u0644\u064a\u0629 '\u0627\u0644\u0633\u0648\u0642' \u0648'JSON' \u0641\u064a \u0631\u062f\u0643. \\n\u0627\u0644\u0625\u062c\u0627\u0628\u0629:\"}"
|
11 |
-
}
|
12 |
-
],
|
13 |
-
"scores_by_category": [
|
14 |
-
{
|
15 |
-
"category": "Paraphrasing",
|
16 |
-
"average_score": 10.0,
|
17 |
-
"count": 6
|
18 |
-
},
|
19 |
-
{
|
20 |
-
"category": "Reading Comprehension",
|
21 |
-
"average_score": 10.0,
|
22 |
-
"count": 17
|
23 |
-
},
|
24 |
-
{
|
25 |
-
"category": "Function Calling",
|
26 |
-
"average_score": 9.666666666666666,
|
27 |
-
"count": 3
|
28 |
-
},
|
29 |
-
{
|
30 |
-
"category": "Dialect Detection",
|
31 |
-
"average_score": 9.090909090909092,
|
32 |
-
"count": 11
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"category": "MMLU",
|
36 |
-
"average_score": 8.925619834710744,
|
37 |
-
"count": 121
|
38 |
-
},
|
39 |
-
{
|
40 |
-
"category": "Sentiment Analysis",
|
41 |
-
"average_score": 8.88888888888889,
|
42 |
-
"count": 9
|
43 |
-
},
|
44 |
-
{
|
45 |
-
"category": "Trust & Safety",
|
46 |
-
"average_score": 8.666666666666666,
|
47 |
-
"count": 30
|
48 |
-
},
|
49 |
-
{
|
50 |
-
"category": "Reasoning & Math",
|
51 |
-
"average_score": 8.604651162790697,
|
52 |
-
"count": 43
|
53 |
-
},
|
54 |
-
{
|
55 |
-
"category": "Entity Extraction",
|
56 |
-
"average_score": 8.6,
|
57 |
-
"count": 5
|
58 |
-
},
|
59 |
-
{
|
60 |
-
"category": "Transliteration",
|
61 |
-
"average_score": 8.166666666666666,
|
62 |
-
"count": 6
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"category": "Instruction Following",
|
66 |
-
"average_score": 8.142857142857142,
|
67 |
-
"count": 7
|
68 |
-
},
|
69 |
-
{
|
70 |
-
"category": "Translation (incl Dialects)",
|
71 |
-
"average_score": 7.972222222222222,
|
72 |
-
"count": 36
|
73 |
-
},
|
74 |
-
{
|
75 |
-
"category": "Summarization",
|
76 |
-
"average_score": 7.25,
|
77 |
-
"count": 8
|
78 |
-
},
|
79 |
-
{
|
80 |
-
"category": "General Knowledge",
|
81 |
-
"average_score": 6.873015873015873,
|
82 |
-
"count": 63
|
83 |
-
},
|
84 |
-
{
|
85 |
-
"category": "Arabic Language & Grammar",
|
86 |
-
"average_score": 6.823529411764706,
|
87 |
-
"count": 17
|
88 |
-
},
|
89 |
-
{
|
90 |
-
"category": "Writing (incl Dialects)",
|
91 |
-
"average_score": 6.681818181818182,
|
92 |
-
"count": 22
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"category": "Hallucination",
|
96 |
-
"average_score": 6.666666666666667,
|
97 |
-
"count": 3
|
98 |
-
},
|
99 |
-
{
|
100 |
-
"category": "Coding",
|
101 |
-
"average_score": 6.0,
|
102 |
-
"count": 3
|
103 |
-
},
|
104 |
-
{
|
105 |
-
"category": "Structuring",
|
106 |
-
"average_score": 5.333333333333333,
|
107 |
-
"count": 3
|
108 |
-
},
|
109 |
-
{
|
110 |
-
"category": "Long Context",
|
111 |
-
"average_score": 5.0,
|
112 |
-
"count": 4
|
113 |
-
},
|
114 |
-
{
|
115 |
-
"category": "RAG QA",
|
116 |
-
"average_score": 4.365853658536586,
|
117 |
-
"count": 41
|
118 |
-
},
|
119 |
-
{
|
120 |
-
"category": "Diacritization",
|
121 |
-
"average_score": 3.3333333333333335,
|
122 |
-
"count": 12
|
123 |
-
}
|
124 |
-
],
|
125 |
-
"scores_by_format": [
|
126 |
-
{
|
127 |
-
"format": "Fill-in-the-blank",
|
128 |
-
"average_score": 10.0,
|
129 |
-
"count": 8
|
130 |
-
},
|
131 |
-
{
|
132 |
-
"format": "Short Answer",
|
133 |
-
"average_score": 10.0,
|
134 |
-
"count": 5
|
135 |
-
},
|
136 |
-
{
|
137 |
-
"format": "MCQ",
|
138 |
-
"average_score": 8.851528384279476,
|
139 |
-
"count": 229
|
140 |
-
},
|
141 |
-
{
|
142 |
-
"format": "Generation",
|
143 |
-
"average_score": 6.469298245614035,
|
144 |
-
"count": 228
|
145 |
-
}
|
146 |
-
]
|
147 |
-
},
|
148 |
-
"config": {
|
149 |
-
"model": "openai/o3",
|
150 |
-
"model_sha": "na",
|
151 |
-
"submitted_time": "2025-05-11 18:21:34",
|
152 |
-
"likes": -1,
|
153 |
-
"params": 999,
|
154 |
-
"license": "closed",
|
155 |
-
"model_source": "API",
|
156 |
-
"model_category": "Large"
|
157 |
-
}
|
158 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|