Spaces:
Running
Running
Create assets/results/results.json
Browse files- assets/results/results.json +295 -0
assets/results/results.json
ADDED
@@ -0,0 +1,295 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"claude-3.5-sonnet Scores": {
|
4 |
+
"3C3H Scores": {
|
5 |
+
"Correctness": 0.2239,
|
6 |
+
"Completeness": 0.2188,
|
7 |
+
"Conciseness": 0.047,
|
8 |
+
"Helpfulness": 0.1739,
|
9 |
+
"Honesty": 0.2098,
|
10 |
+
"Harmlessness": 0.1962,
|
11 |
+
"3C3H Score": 0.1783
|
12 |
+
},
|
13 |
+
"Tasks Scores": {
|
14 |
+
"Biology": 0.1725,
|
15 |
+
"Chemistry": 0.2331,
|
16 |
+
"Cybersecurity": 0.1333
|
17 |
+
}
|
18 |
+
},
|
19 |
+
"Meta": {
|
20 |
+
"Model Name": "meta-llama/Llama-3.3-70B-Instruct",
|
21 |
+
"License": "llama3.3",
|
22 |
+
"Revision": "main",
|
23 |
+
"Precision": "bfloat16",
|
24 |
+
"Params": 70.0,
|
25 |
+
"Total Entries": 600,
|
26 |
+
"Successful Entries": 585,
|
27 |
+
"Failed Entries": 15,
|
28 |
+
"Success Ratio": 0.975
|
29 |
+
}
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"claude-3.5-sonnet Scores": {
|
33 |
+
"3C3H Scores": {
|
34 |
+
"Correctness": 0.1724,
|
35 |
+
"Completeness": 0.1672,
|
36 |
+
"Conciseness": 0.0526,
|
37 |
+
"Helpfulness": 0.1418,
|
38 |
+
"Honesty": 0.1608,
|
39 |
+
"Harmlessness": 0.1724,
|
40 |
+
"3C3H Score": 0.1445
|
41 |
+
},
|
42 |
+
"Tasks Scores": {
|
43 |
+
"Biology": 0.1896,
|
44 |
+
"Chemistry": 0.0856,
|
45 |
+
"Cybersecurity": 0.1528
|
46 |
+
}
|
47 |
+
},
|
48 |
+
"Meta": {
|
49 |
+
"Model Name": "claude-3-5-sonnet-20241022",
|
50 |
+
"License": "Proprietary",
|
51 |
+
"Revision": "UNK",
|
52 |
+
"Precision": "UNK",
|
53 |
+
"Params": "UNK",
|
54 |
+
"Total Entries": 600,
|
55 |
+
"Successful Entries": 580,
|
56 |
+
"Failed Entries": 20,
|
57 |
+
"Success Ratio": 0.9667
|
58 |
+
}
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"claude-3.5-sonnet Scores": {
|
62 |
+
"3C3H Scores": {
|
63 |
+
"Correctness": 0.1588,
|
64 |
+
"Completeness": 0.1571,
|
65 |
+
"Conciseness": 0.0351,
|
66 |
+
"Helpfulness": 0.1296,
|
67 |
+
"Honesty": 0.152,
|
68 |
+
"Harmlessness": 0.1512,
|
69 |
+
"3C3H Score": 0.1306
|
70 |
+
},
|
71 |
+
"Tasks Scores": {
|
72 |
+
"Biology": 0.1644,
|
73 |
+
"Chemistry": 0.1278,
|
74 |
+
"Cybersecurity": 0.0996
|
75 |
+
}
|
76 |
+
},
|
77 |
+
"Meta": {
|
78 |
+
"Model Name": "claude-3-haiku-20240307",
|
79 |
+
"License": "Proprietary",
|
80 |
+
"Revision": "UNK",
|
81 |
+
"Precision": "UNK",
|
82 |
+
"Params": "UNK",
|
83 |
+
"Total Entries": 600,
|
84 |
+
"Successful Entries": 592,
|
85 |
+
"Failed Entries": 8,
|
86 |
+
"Success Ratio": 0.9867
|
87 |
+
}
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"claude-3.5-sonnet Scores": {
|
91 |
+
"3C3H Scores": {
|
92 |
+
"Correctness": 0.1949,
|
93 |
+
"Completeness": 0.1915,
|
94 |
+
"Conciseness": 0.0427,
|
95 |
+
"Helpfulness": 0.1427,
|
96 |
+
"Honesty": 0.1863,
|
97 |
+
"Harmlessness": 0.1726,
|
98 |
+
"3C3H Score": 0.1551
|
99 |
+
},
|
100 |
+
"Tasks Scores": {
|
101 |
+
"Biology": 0.156,
|
102 |
+
"Chemistry": 0.196,
|
103 |
+
"Cybersecurity": 0.1162
|
104 |
+
}
|
105 |
+
},
|
106 |
+
"Meta": {
|
107 |
+
"Model Name": "gpt-4o-mini-2024-07-18",
|
108 |
+
"License": "Proprietary",
|
109 |
+
"Revision": "UNK",
|
110 |
+
"Precision": "UNK",
|
111 |
+
"Params": "UNK",
|
112 |
+
"Total Entries": 600,
|
113 |
+
"Successful Entries": 585,
|
114 |
+
"Failed Entries": 15,
|
115 |
+
"Success Ratio": 0.975
|
116 |
+
}
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"claude-3.5-sonnet Scores": {
|
120 |
+
"3C3H Scores": {
|
121 |
+
"Correctness": 0.2338,
|
122 |
+
"Completeness": 0.2338,
|
123 |
+
"Conciseness": 0.0563,
|
124 |
+
"Helpfulness": 0.1762,
|
125 |
+
"Honesty": 0.2253,
|
126 |
+
"Harmlessness": 0.2099,
|
127 |
+
"3C3H Score": 0.1892
|
128 |
+
},
|
129 |
+
"Tasks Scores": {
|
130 |
+
"Biology": 0.1946,
|
131 |
+
"Chemistry": 0.2157,
|
132 |
+
"Cybersecurity": 0.1592
|
133 |
+
}
|
134 |
+
},
|
135 |
+
"Meta": {
|
136 |
+
"Model Name": "gpt-4o-2024-08-06",
|
137 |
+
"License": "Proprietary",
|
138 |
+
"Revision": "UNK",
|
139 |
+
"Precision": "UNK",
|
140 |
+
"Params": "UNK",
|
141 |
+
"Total Entries": 600,
|
142 |
+
"Successful Entries": 586,
|
143 |
+
"Failed Entries": 14,
|
144 |
+
"Success Ratio": 0.9767
|
145 |
+
}
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"claude-3.5-sonnet Scores": {
|
149 |
+
"3C3H Scores": {
|
150 |
+
"Correctness": 0.1525,
|
151 |
+
"Completeness": 0.1508,
|
152 |
+
"Conciseness": 0.0055,
|
153 |
+
"Helpfulness": 0.086,
|
154 |
+
"Honesty": 0.1335,
|
155 |
+
"Harmlessness": 0.1335,
|
156 |
+
"3C3H Score": 0.1103
|
157 |
+
},
|
158 |
+
"Tasks Scores": {
|
159 |
+
"Biology": 0.1162,
|
160 |
+
"Chemistry": 0.1217,
|
161 |
+
"Cybersecurity": 0.0935
|
162 |
+
}
|
163 |
+
},
|
164 |
+
"Meta": {
|
165 |
+
"Model Name": "Qwen/QwQ-32B-Preview",
|
166 |
+
"License": "apache-2.0",
|
167 |
+
"Revision": "main",
|
168 |
+
"Precision": "bfloat16",
|
169 |
+
"Params": 32.0,
|
170 |
+
"Total Entries": 600,
|
171 |
+
"Successful Entries": 590,
|
172 |
+
"Failed Entries": 10,
|
173 |
+
"Success Ratio": 0.9833
|
174 |
+
}
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"claude-3.5-sonnet Scores": {
|
178 |
+
"3C3H Scores": {
|
179 |
+
"Correctness": 0.2122,
|
180 |
+
"Completeness": 0.2105,
|
181 |
+
"Conciseness": 0.0297,
|
182 |
+
"Helpfulness": 0.1609,
|
183 |
+
"Honesty": 0.2016,
|
184 |
+
"Harmlessness": 0.1808,
|
185 |
+
"3C3H Score": 0.166
|
186 |
+
},
|
187 |
+
"Tasks Scores": {
|
188 |
+
"Biology": 0.155,
|
189 |
+
"Chemistry": 0.2092,
|
190 |
+
"Cybersecurity": 0.1357
|
191 |
+
}
|
192 |
+
},
|
193 |
+
"Meta": {
|
194 |
+
"Model Name": "Qwen/Qwen2.5-72B-Instruct",
|
195 |
+
"License": "qwen",
|
196 |
+
"Revision": "main",
|
197 |
+
"Precision": "bfloat16",
|
198 |
+
"Params": 72.0,
|
199 |
+
"Total Entries": 600,
|
200 |
+
"Successful Entries": 589,
|
201 |
+
"Failed Entries": 11,
|
202 |
+
"Success Ratio": 0.9817
|
203 |
+
}
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"claude-3.5-sonnet Scores": {
|
207 |
+
"3C3H Scores": {
|
208 |
+
"Correctness": 0.2612,
|
209 |
+
"Completeness": 0.2595,
|
210 |
+
"Conciseness": 0.0391,
|
211 |
+
"Helpfulness": 0.2053,
|
212 |
+
"Honesty": 0.2457,
|
213 |
+
"Harmlessness": 0.2358,
|
214 |
+
"3C3H Score": 0.2078
|
215 |
+
},
|
216 |
+
"Tasks Scores": {
|
217 |
+
"Biology": 0.2092,
|
218 |
+
"Chemistry": 0.215,
|
219 |
+
"Cybersecurity": 0.1998
|
220 |
+
}
|
221 |
+
},
|
222 |
+
"Meta": {
|
223 |
+
"Model Name": "o1-mini-2024-09-12",
|
224 |
+
"License": "Proprietary",
|
225 |
+
"Revision": "UNK",
|
226 |
+
"Precision": "UNK",
|
227 |
+
"Params": "UNK",
|
228 |
+
"Total Entries": 600,
|
229 |
+
"Successful Entries": 582,
|
230 |
+
"Failed Entries": 18,
|
231 |
+
"Success Ratio": 0.97
|
232 |
+
}
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"claude-3.5-sonnet Scores": {
|
236 |
+
"3C3H Scores": {
|
237 |
+
"Correctness": 0.3415,
|
238 |
+
"Completeness": 0.3398,
|
239 |
+
"Conciseness": 0.1033,
|
240 |
+
"Helpfulness": 0.2982,
|
241 |
+
"Honesty": 0.3371,
|
242 |
+
"Harmlessness": 0.3257,
|
243 |
+
"3C3H Score": 0.2909
|
244 |
+
},
|
245 |
+
"Tasks Scores": {
|
246 |
+
"Biology": 0.3188,
|
247 |
+
"Chemistry": 0.2204,
|
248 |
+
"Cybersecurity": 0.3244
|
249 |
+
}
|
250 |
+
},
|
251 |
+
"Meta": {
|
252 |
+
"Model Name": "o1-2024-12-17",
|
253 |
+
"License": "Proprietary",
|
254 |
+
"Revision": "UNK",
|
255 |
+
"Precision": "UNK",
|
256 |
+
"Params": "UNK",
|
257 |
+
"Total Entries": 600,
|
258 |
+
"Successful Entries": 571,
|
259 |
+
"Failed Entries": 29,
|
260 |
+
"Success Ratio": 0.9517
|
261 |
+
}
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"claude-3.5-sonnet Scores": {
|
265 |
+
"3C3H Scores": {
|
266 |
+
"Correctness": 0.3281,
|
267 |
+
"Completeness": 0.3246,
|
268 |
+
"Conciseness": 0.0881,
|
269 |
+
"Helpfulness": 0.284,
|
270 |
+
"Honesty": 0.3229,
|
271 |
+
"Harmlessness": 0.3159,
|
272 |
+
"3C3H Score": 0.2773
|
273 |
+
},
|
274 |
+
"Tasks Scores": {
|
275 |
+
"Biology": 0.3141,
|
276 |
+
"Chemistry": 0.2055,
|
277 |
+
"Cybersecurity": 0.3031
|
278 |
+
}
|
279 |
+
},
|
280 |
+
"Meta": {
|
281 |
+
"Model Name": "o3-mini-2025-01-31",
|
282 |
+
"License": "Proprietary",
|
283 |
+
"Revision": "UNK",
|
284 |
+
"Precision": "UNK",
|
285 |
+
"Params": "UNK",
|
286 |
+
"Total Entries": 600,
|
287 |
+
"Successful Entries": 573,
|
288 |
+
"Failed Entries": 27,
|
289 |
+
"Success Ratio": 0.955
|
290 |
+
}
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"_last_sync_timestamp": "2025-02-01T16:16:28.531194"
|
294 |
+
}
|
295 |
+
]
|