Spaces:
Running
Running
Update assets/results/results.json
Browse files- assets/results/results.json +31 -1
assets/results/results.json
CHANGED
@@ -2100,6 +2100,36 @@
|
|
2100 |
}
|
2101 |
},
|
2102 |
{
|
2103 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2104 |
}
|
2105 |
]
|
|
|
2100 |
}
|
2101 |
},
|
2102 |
{
|
2103 |
+
"claude-3.5-sonnet Scores": {
|
2104 |
+
"3C3H Scores": {
|
2105 |
+
"Correctness": 0.8789,
|
2106 |
+
"Completeness": 0.8777,
|
2107 |
+
"Conciseness": 0.292,
|
2108 |
+
"Helpfulness": 0.8627,
|
2109 |
+
"Honesty": 0.8726,
|
2110 |
+
"Harmlessness": 0.8789,
|
2111 |
+
"3C3H Score": 0.7771
|
2112 |
+
},
|
2113 |
+
"Tasks Scores": {
|
2114 |
+
"Question Answering (QA)": 0.7845,
|
2115 |
+
"Reasoning": 0.8083,
|
2116 |
+
"Orthographic and Grammatical Analysis": 0.6828,
|
2117 |
+
"Safety": 0.75
|
2118 |
+
}
|
2119 |
+
},
|
2120 |
+
"Meta": {
|
2121 |
+
"Model Name": "claude-3-7-sonnet-20250219",
|
2122 |
+
"License": "Proprietary",
|
2123 |
+
"Revision": "UNK",
|
2124 |
+
"Precision": "UNK",
|
2125 |
+
"Params": "UNK",
|
2126 |
+
"Total Entries": 279,
|
2127 |
+
"Successful Entries": 278,
|
2128 |
+
"Failed Entries": 1,
|
2129 |
+
"Success Ratio": 0.9964
|
2130 |
+
}
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"_last_sync_timestamp": "2025-02-26T09:52:20.282243"
|
2134 |
}
|
2135 |
]
|