Update assets/results/results.json
Browse files- assets/results/results.json +0 -30
assets/results/results.json
CHANGED
@@ -2129,36 +2129,6 @@
|
|
2129 |
"Success Ratio": 0.9964
|
2130 |
}
|
2131 |
},
|
2132 |
-
{
|
2133 |
-
"claude-3.5-sonnet Scores": {
|
2134 |
-
"3C3H Scores": {
|
2135 |
-
"Correctness": 0.5839,
|
2136 |
-
"Completeness": 0.5791,
|
2137 |
-
"Conciseness": 0.1394,
|
2138 |
-
"Helpfulness": 0.557,
|
2139 |
-
"Honesty": 0.5731,
|
2140 |
-
"Harmlessness": 0.5839,
|
2141 |
-
"3C3H Score": 0.5027
|
2142 |
-
},
|
2143 |
-
"Tasks Scores": {
|
2144 |
-
"Question Answering (QA)": 0.5612,
|
2145 |
-
"Reasoning": 0.6011,
|
2146 |
-
"Orthographic and Grammatical Analysis": 0.0,
|
2147 |
-
"Safety": 0.4687
|
2148 |
-
}
|
2149 |
-
},
|
2150 |
-
"Meta": {
|
2151 |
-
"Model Name": "Conception/aml-arabic-small-2025-02-20",
|
2152 |
-
"License": "mit",
|
2153 |
-
"Revision": "main",
|
2154 |
-
"Precision": "bfloat16",
|
2155 |
-
"Params": 8.0,
|
2156 |
-
"Total Entries": 279,
|
2157 |
-
"Successful Entries": 278,
|
2158 |
-
"Failed Entries": 1,
|
2159 |
-
"Success Ratio": 0.9964
|
2160 |
-
}
|
2161 |
-
},
|
2162 |
{
|
2163 |
"claude-3.5-sonnet Scores": {
|
2164 |
"3C3H Scores": {
|
|
|
2129 |
"Success Ratio": 0.9964
|
2130 |
}
|
2131 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2132 |
{
|
2133 |
"claude-3.5-sonnet Scores": {
|
2134 |
"3C3H Scores": {
|