add o4
Browse files- leaderboard_data.json +6 -38
leaderboard_data.json
CHANGED
|
@@ -16,44 +16,12 @@
|
|
| 16 |
"User Vulnerabilities": 53.6
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"Model": "
|
| 20 |
-
"Average":
|
| 21 |
-
"Assistant Traits":
|
| 22 |
-
"Relationship & Intimacy":
|
| 23 |
-
"Emotional Investment":
|
| 24 |
-
"User Vulnerabilities":
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"Model": "Gemma-3",
|
| 28 |
-
"Average": 95.2,
|
| 29 |
-
"Assistant Traits": 97.9,
|
| 30 |
-
"Relationship & Intimacy": 91.4,
|
| 31 |
-
"Emotional Investment": 95.0,
|
| 32 |
-
"User Vulnerabilities": 96.4
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"Model": "Phi-4",
|
| 36 |
-
"Average": 59.5,
|
| 37 |
-
"Assistant Traits": 79.7,
|
| 38 |
-
"Relationship & Intimacy": 74.2,
|
| 39 |
-
"Emotional Investment": 48.3,
|
| 40 |
-
"User Vulnerabilities": 35.7
|
| 41 |
-
},
|
| 42 |
-
{
|
| 43 |
-
"Model": "GPT-5-mini",
|
| 44 |
-
"Average": 80.5,
|
| 45 |
-
"Assistant Traits": 89.5,
|
| 46 |
-
"Relationship & Intimacy": 84.9,
|
| 47 |
-
"Emotional Investment": 61.7,
|
| 48 |
-
"User Vulnerabilities": 85.7
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"Model": "o3-mini",
|
| 52 |
-
"Average": 74.6,
|
| 53 |
-
"Assistant Traits": 88.1,
|
| 54 |
-
"Relationship & Intimacy": 84.9,
|
| 55 |
-
"Emotional Investment": 71.7,
|
| 56 |
-
"User Vulnerabilities": 53.6
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"Model": "Claude-Sonnet",
|
|
|
|
| 16 |
"User Vulnerabilities": 53.6
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"Model": "o4-mini",
|
| 20 |
+
"Average": 80.8,
|
| 21 |
+
"Assistant Traits": 90.9,
|
| 22 |
+
"Relationship & Intimacy": 86.0,
|
| 23 |
+
"Emotional Investment": 70.0,
|
| 24 |
+
"User Vulnerabilities": 76.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"Model": "Claude-Sonnet",
|